Skip to content

MCP servers › com.mewboard › mewboard

MCP server · registry snapshot 2026-11-17 · last tested 2026-11-17

mewboard MCP server

Registry name com.mewboard/mewboard

by mewboard.com · domain (the registry's namespace rule)repository owner on GitHub: allidevelop (personal account)Source ↗Website ↗

Projects, issues, comments, files, clients and project money in Mewboard, a board shared with AI. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-11-17version 1.0.1streamable HTTP66 tools

Summary

com.mewboard/mewboard is a remote MCP server listed in the official MCP registry at version 1.0.1, under the namespace of the domain mewboard.com. Its linked repository is github.com/allidevelop/mewboard-mcp; GitHub reports its owner as allidevelop, a personal account. On 2026-11-17 ProtocolProbe connected to it in read-only mode and read its inventory: 66 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

  • met: Registry entry is active and says how to run it
  • met: Source repository link opens
  • met: Repository is not archived
  • met: Code pushed to the repository in the 90 days before our check
  • not met: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Repository
public
Tools
66
Last tested
2026-11-17

Tool list size

17,403 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (66 tools). Counted with Anthropic's token counter on 2026-11-17, from the tool list we read on 2026-11-17. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-17 (app.mewboard.com), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.0.1).

Add to your client

Observed fact

This server accepted a session without any credential and lists 32 tools whose name or declaration suggests they change data (create_project, update_project, create_issue, update_issue, delete_issue and 27 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-17.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-17
Mode
read-only (no tool calls)
Latest version
1.0.1, published 2026-11-16 (registry, as of the 2026-11-17 snapshot)
First listed version
2026-11-16 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, all on 2026-11-16; 2 in the 90 days before the 2026-11-17 snapshot.
Most recent 2 versions
  • 1.0.1 · 2026-11-16
  • 1.0.0 · 2026-11-16
(versions still listed in the registry only)
Registry data
snapshot 2026-11-17
Package and repository
checked 2026-11-17
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-16, listed on 2026-11-17 with version 1.0.1 (published 2026-11-16).

Source: the official MCP Registry list on 2026-11-16 and on 2026-11-17.

What it is

What does this server offer?

Observed inventory
66tools
0resources
0prompts

None of its 66 tools are described as changing anything. For 66 the reading was uncertain, so no mark is shown.

  • get_mewboard_guide

    “What Mewboard can do and which tool does what, with typical requests.”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • “List all projects with issue counts per status.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input
    • with_moneyboolean
  • “Get one project by key (e.g.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • projectstringrequired
  • create_projecton 110 other servers

    “Create a project.”

    Publisher declares: read-only no · destructive no · open-world no

    12 inputs, 1 required
    • namestringrequired
    • keystring“1-8 letters/digits, e.g.”
    • descriptionstring
    • statusstring
    • start_datestring“planned start, YYYY-MM-DD”
    • target_datestring“planned finish, YYYY-MM-DD”
    • clientstring“the client the project is for: a client name or id (see list_clients / create_client)”
    • iconstring“one emoji that fits the project, shown instead of the first letter of its key, e.g.”
    • templatestring“id of an own project template of the workspace (see list_templates): the project starts with its statuses, fields, milestones, issues and checklists”
    • parentstring“make it a sub-project of this project (key or id); at most 3 levels deep”
    • budgetnumber or string“the agreed budget amount”
    • budget_currencystring“UAH, USD, EUR...”
  • update_projecton 42 other servers

    “Update project name/description/status/dates.”

    Publisher declares: read-only no · destructive yes · open-world no

    13 inputs, 1 required
    • projectstringrequired
    • namestring
    • keystring
    • descriptionstring
    • statusstring
    • start_datestring or null“YYYY-MM-DD; "" or null clears it”
    • target_datestring or null“YYYY-MM-DD; "" or null clears it”
    • clientstring or null“client name or id; "" or null removes the client”
    • iconstring or null“an emoji shown instead of the first letter of the key; "" or null goes back to the letter”
    • parentstring or null“move it under another project (key or id) as a sub-project; "" or null = back to the top level”
    • budgetnumber or string or null“the agreed budget (change it whenever the work grows); null clears it, then the total of the tasks is the budget”
    • budget_currencystring“currency of the budget: UAH, USD, EUR...”
    • budget_fieldstring or null“the NAME of the number / money / formula field whose total is the cost of the tasks”
  • “List/filter issues.”

    Publisher declares: read-only yes · destructive no · open-world no

    10 inputs
    • projectstring“project key or id”
    • include_subprojectsboolean“with project: also the issues of all its sub-projects”
    • statusstring
    • milestone_idstring
    • assigneestring“a member name or "me" (the caller); also matches text assignees”
    • prioritystring
    • labelstring
    • clientstring“issues of this client (its own or its project's): a client name or id”
    • querystring
    • limitnumber
  • “Get an issue (by identifier like WEB-12 or id) including its attachment list and checklists with item ids (no comments or file contents).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • issuestringrequired
  • create_issueon 3 other servers

    “Create an issue (task) in a project.”

    Publisher declares: read-only no · destructive no · open-world no

    13 inputs, 2 required
    • projectstringrequired“project key or id”
    • titlestringrequired
    • descriptionstring
    • statusstring“one of the 6 kinds backlog, todo, in_progress, in_review, done, canceled, or the NAME of one of the project's own statuses (get_project -> statuses); a kind pi…”
    • prioritystring
    • assigneestring“a member name (see list_members) or "me"; any other text is kept as a free-text assignee”
    • labelsarray
    • milestone_idstring
    • due_datestring“due date, YYYY-MM-DD”
    • start_datestring“planned start, YYYY-MM-DD”
    • created_bystring“who is creating it, e.g.”
    • clientstring“client name or id; when omitted the issue belongs to its project's client”
    • fieldsobject“custom fields of the project (see list_fields): { "Field name": value }: text, a number, "YYYY-MM-DD", one option, a list of options, a https:// link, a member…”
  • update_issueon 3 other servers

    “Update an issue: change status (move on the board), priority, assignee, labels, milestone, title or description.”

    Publisher declares: read-only no · destructive yes · open-world no

    12 inputs, 1 required
    • issuestringrequired
    • titlestring
    • descriptionstring
    • statusstring“one of the 6 kinds backlog, todo, in_progress, in_review, done, canceled, or the NAME of one of the project's own statuses (get_project -> statuses); a kind pi…”
    • prioritystring
    • assigneestring“a member name (see list_members) or "me" (notifies that person unless it is you); other text = free-text assignee; "" clears”
    • labelsarray
    • milestone_idstring
    • due_datestring or null“due date YYYY-MM-DD; "" or null clears it”
    • start_datestring or null“planned start YYYY-MM-DD; "" or null clears it”
    • clientstring or null“client name or id for this issue only; "" or null = back to the project's client”
    • fieldsobject“set custom fields (see list_fields): { "Field name": value }; null or "" clears one”
  • delete_issueon 2 other servers

    “Delete an issue: it moves to the trash with its comments and attachments and is erased for good when the trash period of the server ends (14 days by default; it can be restored in the web app until t…”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • issuestringrequired
  • add_checklist

    “Add a named checklist to an issue.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 2 required
    • issuestringrequired“identifier like WEB-12, or id”
    • titlestringrequired“name of the checklist, e.g.”
    • itemsarray“item texts, in order”
  • add_checklist_itemon 2 other servers

    “Add one item to an existing checklist (use the checklist id from get_issue / read_issue).”

    Publisher declares: read-only no · destructive no · open-world no

    2 inputs, 2 required
    • checklist_idstringrequired
    • textstringrequired
Show 54 more tools
  • update_checklist_itemon 1 other server

    “Tick or untick a checklist item (done true/false) and/or change its text.”

    Publisher declares: read-only no · destructive yes · open-world no

    3 inputs, 1 required
    • item_idstringrequired
    • doneboolean
    • textstring
  • delete_checkliston 2 other servers

    “Delete a whole checklist with its items.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • checklist_idstringrequired
  • set_project_statuses

    “Give a project its own statuses (board columns), e.g.”

    Publisher declares: read-only no · destructive yes · open-world no

    2 inputs, 2 required
    • projectstringrequired
    • statusesarrayrequired
  • list_notificationson 24 other servers

    “What is new FOR ME: changes by other people (or their agents) in the issues I follow, @mentions, assignments and my reminders, newest first.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs
    • unread_onlyboolean
    • projectstring“only this project (key or id)”
    • limitnumber“default 30, max 100”
  • mark_notifications_readon 10 other servers

    “Mark all my notifications as read (the bell count goes to zero).”

    Publisher declares: read-only no · destructive no · open-world no

    Takes no inputs.

  • follow_issue

    “Follow an issue: hear about its comments, status and due date changes, checklists and files.”

    Publisher declares: read-only no · destructive no · open-world no

    1 input, 1 required
    • issuestringrequired
  • unfollow_issue

    “Stop following an issue (an @mention or a new comment of yours makes you follow it again).”

    Publisher declares: read-only no · destructive no · open-world no

    1 input, 1 required
    • issuestringrequired
  • list_followingon 4 other servers

    “The issues I follow in this workspace (newest change first) and why: author, assignee, comment, mention or follow.”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • set_project_notificationson 1 other server

    “How much I hear about a project: all (every change and every new issue), mine (only the issues I follow; the default) or mute (only @mentions).”

    Publisher declares: read-only no · destructive no · open-world no

    2 inputs, 2 required
    • projectstringrequired
    • levelstringrequired
  • list_templateson 138 other servers

    “List the own templates of the workspace: kind project (start a project from it with create_project template) or workspace (offered when a new workspace is created in the app).”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • save_project_as_templateon 1 other server

    “Save a project as a template of the workspace: its statuses, custom fields, milestones and (unless issues=false) its open issues with their checklists, unticked, and (unless subprojects=false) its su…”

    Publisher declares: read-only no · destructive no · open-world no

    4 inputs, 1 required
    • projectstringrequired
    • namestring“template name; default = the project name”
    • issuesboolean“default true: keep the issues and checklists as starter tasks”
    • subprojectsboolean“default true: keep its sub-projects in the template”
  • “Read one own template of the workspace with all its projects, statuses, fields, milestones, starter tasks and checklists (see list_templates for ids).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • templatestringrequired
  • create_templateon 24 other servers

    “Create an own template of the workspace from scratch, e.g.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 1 required
    • namestringrequired
    • kindstring
    • projectsarray“the projects; default one empty project named like the template”
  • update_templateon 21 other servers

    “Replace the content of an own template (its author or an administrator): name and/or the whole list of projects.”

    Publisher declares: read-only no · destructive yes · open-world no

    3 inputs, 1 required
    • templatestringrequired
    • namestring
    • projectsarray
  • “Issues (and projects) in the trash, restorable for a while (14 days by default).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input
    • projectstring“only this project (key or id)”
  • restore_issue

    “Bring an issue back from the trash (see list_trash).”

    Publisher declares: read-only no · destructive no · open-world no

    1 input, 1 required
    • issuestringrequired
  • “List the custom fields of a project (name, type, options, currency of money fields, formula of formula fields).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • projectstringrequired
  • create_fieldon 4 other servers

    “Add a custom field to a project, e.g.”

    Publisher declares: read-only no · destructive no · open-world no

    7 inputs, 3 required
    • projectstringrequired
    • namestringrequired
    • typestringrequired
    • formulastring“the formula of a formula field, e.g.”
    • currencystring“the currency of a money field (default USD), or of a formula field whose result is an amount”
    • optionsarray“the choices of a select / multi field”
    • on_cardboolean“show the value on the board cards”
  • update_fieldon 5 other servers

    “Rename a custom field (formulas that use it follow), change its options, its formula, the currency of a money or formula field (amounts stay as they are) or whether it shows on cards (the type cannot…”

    Publisher declares: read-only no · destructive yes · open-world no

    6 inputs, 1 required
    • formulastring“formula fields: the new formula”
    • fieldstringrequired“field id (see list_fields)”
    • namestring
    • optionsarray
    • on_cardboolean
    • currencystring“money fields: UAH, USD, EUR, GBP, PLN...”
  • try_formula

    “Try a formula on the newest issues of a project before saving it as a formula field: returns each issue's result, or the mistake in the formula.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs, 2 required
    • projectstringrequired
    • formulastringrequired
    • namestring“the name of the formula field being edited, if any (it may not use itself)”
  • delete_fieldon 4 other servers

    “Delete a custom field of a project together with its values in every issue.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • fieldstringrequired“field id (see list_fields)”
  • list_milestoneson 3 other servers

    “List milestones of a project with progress (issue_done / issue_total).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • projectstringrequired
  • “List the members of the workspace (people and agent accounts) an issue can be assigned to.”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • get_project_totals

    “The money of a project (sub-projects included unless subprojects=false): the total of every number / money / payments / numeric formula field (summed by field name, other currencies converted at toda…”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • projectstringrequired
    • subprojectsboolean
  • get_client_totals

    “The money of all projects of a client: per project (see get_project_totals) and the totals of the fields across them.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • clientstringrequired“client id (see list_clients)”
  • import_issues

    “Create many issues of one project at once (up to 2000), e.g.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 2 required
    • projectstringrequired
    • issuesarrayrequired“one object per issue; fields as on create_issue (payments = a list of {amount, currency?, date, paid, note})”
    • fieldsarray“fields to create first when the project has none of that name”
  • get_money_report

    “The money report of the workspace, from the payments fields of every project you can see: received, expenses (negative payments), net, expected and overdue money; by month, by project and by client; …”

    Publisher declares: read-only yes · destructive no · open-world no

    6 inputs
    • currencystring“UAH, USD, EUR...”
    • fromstring“YYYY-MM-DD: received payments from this day”
    • tostring“YYYY-MM-DD: up to this day”
    • projectstring“one project (key or id) with its sub-projects”
    • clientstring“one client id (see list_clients)”
    • rowsboolean“include every payment (default false: totals, months, projects and clients only)”
  • “List the clients of the workspace (the people or companies projects are for) with their projects and the number of open issues.”

    Publisher declares: read-only yes · destructive no · open-world no

    Takes no inputs.

  • create_clienton 15 other servers

    “Create a client (a person or company).”

    Publisher declares: read-only no · destructive no · open-world no

    5 inputs, 1 required
    • namestringrequired
    • companystring
    • emailstring
    • phonestring
    • notesstring
  • update_clienton 6 other servers

    “Update a client (name, company, email, phone, notes).”

    Publisher declares: read-only no · destructive yes · open-world no

    6 inputs, 1 required
    • clientstringrequired
    • namestring
    • companystring or null
    • emailstring or null
    • phonestring or null
    • notesstring or null
  • delete_clienton 1 other server

    “Delete a client.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • clientstringrequired
  • create_milestoneon 1 other server

    “Create a milestone in a project.”

    Publisher declares: read-only no · destructive no · open-world no

    5 inputs, 2 required
    • projectstringrequired
    • namestringrequired
    • descriptionstring
    • target_datestring“YYYY-MM-DD”
    • statusstring
  • update_milestoneon 1 other server

    “Update a milestone.”

    Publisher declares: read-only no · destructive yes · open-world no

    5 inputs, 1 required
    • milestone_idstringrequired
    • namestring
    • descriptionstring
    • target_datestring or null
    • statusstring
  • delete_milestone

    “Delete a milestone (its issues stay, unassigned).”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • milestone_idstringrequired
  • list_commentson 31 other servers

    “List comments on an issue (issue=WEB-12) or on a project (project=WEB), with their attachment metadata.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs
    • issuestring
    • projectstring
  • “Add a Markdown comment to an issue or to a project (give exactly one of issue/project).”

    Publisher declares: read-only no · destructive no · open-world no

    4 inputs, 1 required
    • issuestring
    • projectstring
    • bodystringrequired
    • authorstring
  • update_commenton 7 other servers

    “Edit a comment body and / or pin it (pinned: true) or unpin it (false).”

    Publisher declares: read-only no · destructive yes · open-world no

    3 inputs, 1 required
    • comment_idstringrequired
    • bodystring
    • pinnedboolean
  • delete_commenton 14 other servers

    “Delete a comment.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • comment_idstringrequired
  • “Create a questionnaire for a client in a project (platform owner only).”

    Publisher declares: read-only no · destructive no · open-world no

    7 inputs, 2 required
    • projectstringrequired
    • titlestringrequired
    • descriptionstring
    • thanksstring
    • issuestring
    • markdownstring
    • questionsarray
  • “Edit a questionnaire: title, description, thanks message, task, questions (list or markdown), status open/closed, or regenerate=true for a new link (the old one stops working).”

    Publisher declares: read-only no · destructive yes · open-world no

    9 inputs, 1 required
    • form_idstringrequired
    • titlestring
    • descriptionstring
    • thanksstring
    • issuestring
    • markdownstring
    • questionsarray
    • statusstring
    • regenerateboolean
  • “List the questionnaires of a project with their links and answer counts (platform owner only).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • projectstringrequired
  • list_form_responseson 3 other servers

    “Read the answers clients sent to a questionnaire: the form with its questions, and every response keyed by question id (platform owner only).”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • form_idstringrequired
  • “Upload a file and attach it to an issue, project, or comment.”

    Publisher declares: read-only no · destructive no · open-world no

    6 inputs, 2 required
    • filenamestringrequired“e.g.”
    • content_base64stringrequired“the file bytes, base64-encoded”
    • mimestring“e.g.”
    • issuestring
    • projectstring
    • comment_idstring
  • read_issue

    “READ EVERYTHING about an issue in one call: fields, full description, ALL comments, and the content of ALL files — attached to the issue, attached to comments, or linked in Markdown.”

    Publisher declares: read-only yes · destructive no · open-world no

    4 inputs, 1 required
    • issuestringrequired“identifier like WEB-12, or id”
    • include_mediaboolean“default true: also return the content of every file (images viewable, text inline, zip listings, others saved locally)”
    • max_imagesnumber“max images returned inline (default 12)”
    • raw_filesboolean“default false: ALSO attach every PDF/Office/other binary file untouched as an embedded document (up to 20 MB each), for clients that read such files natively”
  • read_projecton 3 other servers

    “READ EVERYTHING about a project in one call: description, ALL project-level comments, and the content of ALL files attached to the project, its comments, or linked in Markdown (same output format as …”

    Publisher declares: read-only yes · destructive no · open-world no

    4 inputs, 1 required
    • projectstringrequired“project key or id”
    • include_mediaboolean“default true: also return the content of every file (images viewable, text inline, zip listings, others saved locally)”
    • max_imagesnumber“max images returned inline (default 12)”
    • raw_filesboolean“default false: ALSO attach every PDF/Office/other binary file untouched as an embedded document (up to 20 MB each), for clients that read such files natively”
  • read_attachmenton 3 other servers

    “Read ONE attachment.”

    Publisher declares: read-only yes · destructive no · open-world no

    2 inputs, 1 required
    • attachmentstringrequired
    • rawboolean“default false: ALSO return the original file untouched as an embedded document (up to 20 MB), for clients that read PDFs / Office files natively”
  • list_attachmentson 4 other servers

    “List attachments of an issue, of a project (the files on the project Overview, not those of its issues) or of a comment.”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs
    • issuestring
    • projectstring
    • comment_idstring
  • delete_attachmenton 6 other servers

    “Delete an attachment.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • attachment_idstringrequired
  • create_reminderon 8 other servers

    “Remind a person about an issue, a project or a comment at a time.”

    Publisher declares: read-only no · destructive no · open-world no

    8 inputs
    • issuestring
    • projectstring
    • comment_idstring
    • atstring
    • in_minutesnumber
    • notestring
    • repeatstring
    • userstring
  • list_reminderson 9 other servers

    “List the reminders of the token owner (pending, and the ones that fired in the last 7 days).”

    Publisher declares: read-only yes · destructive no · open-world no

    3 inputs
    • issuestring
    • projectstring
    • statusstring
  • delete_reminderon 6 other servers

    “Cancel (delete) a reminder of the token owner.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • reminder_idstringrequired
  • “List the change history as batches, newest first: who changed what (issue fields, created / trashed / restored issues, added / edited / deleted comments), grouped into batches (changes by one person …”

    Publisher declares: read-only yes · destructive no · open-world no

    4 inputs
    • issuestring
    • projectstring
    • limitnumber
    • beforenumber“only changes with an id lower than this (paging)”
  • undo_changes

    “Undo a whole batch (give batch = the batch id from list_changes) or selected changes (change_ids).”

    Publisher declares: read-only no · destructive yes · open-world no

    2 inputs
    • batchstring
    • change_idsarray
  • “Full-text-ish search over issue titles/descriptions and projects.”

    Publisher declares: read-only yes · destructive no · open-world no

    1 input, 1 required
    • querystringrequired

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-17.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
36% of 216
Tools with a description
100% of 66
Typical description length
257 characters

The tool set

Counted from the listing

Tools
66
Size of the list
about 13,277 tokens for an agent to load (characters ÷ 4)
Naming
65 of 66 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 66 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-17 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://app.mewboard.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "mewboard": {
      "url": "https://app.mewboard.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "mewboard": {
      "type": "http",
      "url": "https://app.mewboard.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mewboard","type":"http","url":"https://app.mewboard.com/mcp"}'
Claude Code
claude mcp add --transport http mewboard https://app.mewboard.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "mewboard": {
      "type": "streamableHttp",
      "url": "https://app.mewboard.com/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "mewboard": {
      "httpUrl": "https://app.mewboard.com/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.mewboard]
url = "https://app.mewboard.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "mewboard": {
      "url": "https://app.mewboard.com/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://app.mewboard.com/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-17. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-17. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-17. Source: read 2026-11-17.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-17. Source: read 2026-11-17.

Own host

  • security.txt. No security.txt at https://app.mewboard.com/.well-known/ (HTTP 404, 2026-11-17). No security.txt at https://mewboard.com/.well-known/ (HTTP 404, 2026-11-17). Source: app.mewboard.com/.well-known/security.txt · read 2026-11-17.
  • A2A agent card. No A2A agent card at https://app.mewboard.com/.well-known/ (HTTP 404, 2026-11-17). No A2A agent card at https://mewboard.com/.well-known/ (HTTP 404, 2026-11-17). Source: app.mewboard.com/.well-known/agent-card.json · read 2026-11-17.

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint app.mewboard.com/mcpSession openedmatchesour test · 2026-11-17
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-17
Repository github.com/allidevelop/mewboard-mcpOpens publiclymatchesapi.github.com · 2026-11-17

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
com.mewboard
GitHub owner
a personal account (allidevelop)
Repository
github.com/allidevelop/mewboard-mcp
Stars
0
Repository age
0–30 days
Last push
0–30 days ago
Archived
no
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-11-17; security policy read from GitHub · 2026-11-17.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 0 stars (ranked from 10)
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • MetSource repository link opensThe linked GitHub repository is public.
  • MetRepository is not archivedNot archived.
  • MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
  • Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-17 (security policy 2026-11-17). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about com.mewboard/mewboard

Answered from the data above

Who publishes com.mewboard/mewboard?

The registry ties the namespace com.mewboard to the domain mewboard.com; only its owner can publish under it. Its linked repository is github.com/allidevelop/mewboard-mcp; GitHub reports its owner as allidevelop, a personal account. These are facts from the registry and GitHub, not a rating.

Is com.mewboard/mewboard safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does com.mewboard/mewboard need an API key or sign-in?

It opened a session without any credential on 2026-11-17. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.mewboard/mewboard been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Does com.mewboard/mewboard publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of com.mewboard/mewboard?

In github.com/allidevelop/mewboard-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-17
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-11-17, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,884 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 66 tools, 0 resources, 0 prompts.
  4. 4,775 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-17; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
not stated
GitHub detects no source language in this repository (docs-only or empty)
Hosting type
registry · 2026-11-17
MCP capability
tools
our test · 2026-11-17
Transport
streamable HTTP
registry · 2026-11-17
Required credentials
none declared
registry · 2026-11-17 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-17
Lifecycle status
registry · 2026-11-17
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
owner: a personal account · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-11-17
Maintenance
api.github.com · 2026-11-17
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-17

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.mewboard/mewboard: MCP server record.” Data checked 2026-11-17. https://protocolprobe.com/mcp/servers/com.mewboard/mewboard

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 4 of 5 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.mewboard/mewboard)](https://protocolprobe.com/mcp/servers/com.mewboard/mewboard)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology