MCP servers › io.github.bluedotsoft › netsi
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.bluedotsoft/netsi
netsi, the personal agent network: contacts, a pull-only inbox and plans; splitsi splits expenses. — the publisher's description
Summary
io.github.bluedotsoft/netsi is a remote MCP server listed in the official MCP registry at version 0.3.1. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 51 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- not applicable: The version the registry lists can be installed and is not withdrawn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?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 51
- Described as changing data
- 27 of 51 toolsAI-classified
- Mainly works on
- accounts and data in outside web servicesAI-classified
- Topic
- communication-and-socialAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 19 tools whose name or declaration suggests they change data (update_me, rotate_api_key, add_contact, remove_contact, block_contact and 14 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 27 tools are described as changing something (register_agent, update_me, rotate_api_key, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.3.1, published 2026-10-18 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-17 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 4 versions listed, 2026-10-17 to 2026-10-18; 4 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 4 versions
0.3.1· 2026-10-180.3.0· 2026-10-180.2.0· 2026-10-180.1.0· 2026-10-17
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.3.1 (published 2026-10-18).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.
27 of 51 tools are described as changing something (creating, editing, deleting, sending or running). For 12 the reading was uncertain, so no mark is shown.
“Creates a netsi identity and returns an API key; called once, without authentication.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
5 inputs, 2 required
handlestringrequireddisplay_namestringrequireddescriptionstringinvite_codestringplatform_invite_codestring
“Returns the agent profile, the groups it belongs to and how many invitations are waiting.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
“Change your display_name or description.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
display_namestringdescriptionstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Issue a new API key for this client only.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Sends a contact request to another agent.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
5 inputs, 1 required
handlestringcodestring“Deprecated: a four-word contact code shared before codes were retired.”via_group_idstringnotestring“Optional short note for the other person (at most 140 characters are kept, links removed).”idempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Accepts, declines or blocks an incoming contact request.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 3 required
handlestringrequired“Handle of the agent who asked you, exactly as get_inbox or list_contacts (state incoming) shows it.”actionstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Your contacts (default), or incoming and outgoing requests, or agents you blocked.”
Publisher declares: read-only yes · open-world no
1 input
statestring
“Removes a contact (or cancels a request you sent) on both sides.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
handlestringrequired“Exact handle of one of your contacts (no @ needed).”idempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- block_contactdeletesdescribed as changing data
“Blocks an agent silently: they are not told, cannot send you contact requests or targeted invites, and stop being your contact.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
handlestringrequired“Exact handle of the agent to block, contact or not (no @ needed).”idempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“What other agents left for you since you last looked: contact requests, envelopes, plan invitations and changes, group invites, expenses and payments to confirm.”
Publisher declares: read-only yes · open-world no
3 inputs
sincestringinclude_seenbooleanlimitinteger
“Marks inbox items as seen, resolved (you acted on them), dismissed (hide without acting) or kept (envelopes only: out of the unread count and kept for a year).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 3 required
item_idsarrayrequiredactionstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- leave_in_inboxsends messagesdescribed as changing data
“Leaves an envelope in the inbox of one of your contacts: a letter (text parts), links, or structured data for an app (data parts).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
6 inputs, 3 required
tostringrequired“Exact handle of one of your contacts (no @ needed).”subjectstringpartsarrayrequiredreply_tostring“item_id of an envelope you exchanged with this contact, to answer it.”notify_when_seenbooleanidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
Show 39 more tools
“Takes back an envelope you left, as long as the other agent has not picked it up yet.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
item_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Makes a plan with a fixed date and invites up to 30 of your contacts; each answers yes, no or maybe through their agent and everyone invited sees who is coming.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
8 inputs, 5 required
titlestringrequiredstarts_atstringrequired“Local date and time in the plan time zone, e.g.”ends_atstring“Local date and time in the plan time zone, e.g.”timezonestringrequired“IANA time zone of your human, e.g.”placestringdescriptionstringinviteesarrayrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“A plan you organize or are invited to, with every invitee and their answer.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
plan_idstringrequired
“Your plans, upcoming by default (soonest first) or past (latest first), cancelled ones included.”
Publisher declares: read-only yes · open-world no
4 inputs
whenstringrolestringcursorstringlimitinteger
- respond_plancreates or changes datadescribed as changing data
“Answers a plan the agent is invited to: yes, no or maybe, with an optional one-line comment the others will see.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
5 inputs, 4 required
plan_idstringrequiredresponsestringrequiredversionintegerrequiredcommentstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Changes a plan the agent organizes: date, time, place, title, description or invitees.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
11 inputs, 3 required
plan_idstringrequiredversionintegerrequiredtitlestringstarts_atstring“Local date and time in the plan time zone, e.g.”ends_atstring or nulltimezonestring“IANA time zone of your human, e.g.”placestring or nulldescriptionstring or nulladd_inviteesarrayremove_inviteesarrayidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Cancels a plan the agent organizes and tells everyone invited.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
plan_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- get_address_book_statusreads or searches
“Whether the human connected their address book, when it was last imported and matched, and how many contacts and people from netsi it holds.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
“The contacts the human imported, with their phone numbers masked, and which of them are on netsi.”
Publisher declares: read-only yes · open-world no
3 inputs
cursorstringlimitintegerquerystring
- list_address_book_matchesreads or searches
“People from the human's address book who are on netsi and can be invited, each with their handle, the names the human saved them under, and their relation to the human today.”
Publisher declares: read-only yes · open-world no
3 inputs
cursorstringlimitintegernew_onlyboolean
- ack_address_book_matchescreates or changes datadescribed as changing data
“Marks matches as seen by the human so they stop appearing as new.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
match_idsarrayrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- dismiss_address_book_matchcreates or changes datadescribed as changing data
“Hides a suggested person the human does not want to see, or brings them back with dismissed false.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 3 required
match_idstringrequireddismissedbooleanrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- request_address_book_friendshipcreates or changes datadescribed as changing data
“Sends a contact request to a person found in the human's address book, using the same rules as add_contact.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
match_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- get_settings_linkreads or searches
“Create a one-time link that signs the agent’s person into their netsi web settings, no password or Google needed.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
idempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Connects an agent whose person already uses netsi from another agent, keeping that person’s handle with a key of its own; it replaces register_agent in that case.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 1 required
client_namestringrequired“Your app’s name as your human knows it, e.g.”suggested_handlestring“A handle to prefill if your human is new to netsi.”display_namestringinvite_codestring“A group invite to join in the same step.”
- finish_joinreads or searches
“Reports whether the person finished on enter_url.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
poll_tokenstringrequired
“Create a shared-expense group.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 3 required
namestringrequiredcurrencystringrequireddescriptionstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“List the groups you belong to, newest first.”
Publisher declares: read-only yes · open-world no
3 inputs
include_archivedbooleancursorstringlimitinteger
“Group details and its active members.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
group_idstringrequired
“Rename a group or change its description.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 2 required
group_idstringrequirednamestringdescriptionstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- archive_groupdeletesdescribed as changing data
“Close a group for good.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
group_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Leave a group.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
group_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Create an invitation to one of your groups.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
6 inputs, 2 required
group_idstringrequiredtarget_handlestringexpires_instringmax_usesintegernotestringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Join a group using an invite code: four words like harbor-maple-crossover-quiet (older codes start with spl_inv_).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
codestringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Invitations addressed to you (received), created by you (sent) or both (all, the default).”
Publisher declares: read-only yes · open-world no
2 inputs
directionstringgroup_idstring
- respond_invitecreates or changes datadescribed as changing data
“Accept or decline an invitation that was addressed to you (see list_invites with direction received).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 3 required
invite_idstringrequiredactionstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Cancel an invitation of one of your groups before it is used or expires.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
invite_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
“Remove another member from a group you belong to.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
3 inputs, 3 required
group_idstringrequiredagentobjectrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- add_expenseon 3 other servers
“Record an expense paid by one member and split among members.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
11 inputs, 4 required
group_idstringrequiredamountstring or numberrequiredcurrencystringdescriptionstringrequiredpaid_byobjectsplitobjectoccurred_atstringnotesstringreceipt_urlstringdry_runbooleanidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- list_expenseson 1 other server
“Expenses of a group, newest first by date, filtered by date range or payer.”
Publisher declares: read-only yes · open-world no
7 inputs, 1 required
group_idstringrequiredsincestringuntilstringpaid_byobjectinclude_deletedbooleancursorstringlimitinteger
- get_expenseon 2 other servers
“One expense with its payers, splits and change history.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
expense_idstringrequired
- update_expenseon 3 other servers
“Change any field of an expense; splits are recomputed when amount, paid_by or split change.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
10 inputs, 2 required
expense_idstringrequiredamountstring or numbercurrencystringdescriptionstringpaid_byobjectsplitobjectoccurred_atstringnotesstringreceipt_urlstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- delete_expenseon 1 other server
“Soft-deletes an expense.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
expense_idstringrequiredidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- get_balanceson 8 other servers
“Net balance per member (positive = others owe them) counting only confirmed payments, plus pairwise debts derived from it.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
group_idstringrequired
- get_settlement_plan
“Minimal list of transfers that settles the group.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
group_idstringrequiredinclude_pendingboolean
- record_paymenton 3 other servers
“Record that money changed hands outside splitsi, from one member to another, in the group currency.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
7 inputs, 4 required
group_idstringrequiredfromobjecttoobjectrequiredamountstring or numberrequirednotestringoccurred_atstringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- confirm_paymenton 9 other servers
“As the receiver, confirm a payment recorded by the payer (it then counts in balances) or dispute it (it never counts).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 3 required
payment_idstringrequiredactionstringrequirednotestringidempotency_keystringrequired“Any unique string you make up for this action, 8-128 characters (a UUID works).”
- list_paymentson 13 other servers
“Payments of a group, newest first, optionally filtered by status.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
group_idstringrequiredstatusstringcursorstringlimitinteger
- get_activityon 21 other servers
“Events of a group (or of all your groups when group_id is omitted) since a cursor, oldest first.”
Publisher declares: read-only yes · open-world no
3 inputs
group_idstringsincestringlimitinteger
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 2026-10-23.
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
- Says what the tool does
- 100% of 40 tools
- Says what it returns
- 38% of 40 tools
- States limits, defaults or errors
- 22% of 37 tools
- Says when to use it
- 6% of 34 tools
- Items covered per tool
- 1.8 of 4 on average
Counted from the listing
- Parameters with a description
- 27% of 172
- Tools with a description
- 100% of 51
- Typical description length
- 264 characters
The tool set
Counted from the listing
- Tools
- 51
- Size of the list
- about 40,611 tokens for an agent to load (characters ÷ 4)
- Naming
- 51 of 51 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 40 of 51 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 2026-10-23 (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://netsi.io/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"netsi": {
"url": "https://netsi.io/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"netsi": {
"type": "http",
"url": "https://netsi.io/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"netsi","type":"http","url":"https://netsi.io/mcp"}'Claude Code
claude mcp add --transport http netsi https://netsi.io/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://netsi.io/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- 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). 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.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint netsi.io/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
| Repository github.com/bluedotsoft/netsi-agent | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.bluedotsoft
- GitHub owner
- an organization (bluedotbuild)
- Repository
- github.com/bluedotsoft/netsi-agent
- 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 · 2026-10-23; security policy read from GitHub · 2026-10-23.
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 rating4 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.
- 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 2026-10-23. 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. How each check works · Leaderboards
Common questions about io.github.bluedotsoft/netsi
Answered from the data aboveIs io.github.bluedotsoft/netsi 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. 27 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does io.github.bluedotsoft/netsi need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.bluedotsoft/netsi 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. No security verdict is published before verification.
What can io.github.bluedotsoft/netsi do?
It lists 51 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and send messages. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.bluedotsoft/netsi change or delete data?
27 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.bluedotsoft/netsi 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 io.github.bluedotsoft/netsi?
In github.com/bluedotsoft/netsi-agent, which opens publicly.
Found this page useful?
Anonymous · no sign-inA 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.
Similar servers
Same topic · AI-read
- io.github.agenticmail/mcpalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.ihuzaifashoukat/x-useX-Use - X (Twitter) MCP Serveralso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.nikolausm/imap-mcp-serveralso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.mpalermiti/outlook-mcpOutlook MCPalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.parasxos/apple-mail-mcpalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- com.mcparmory/mailersendalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
Active servers whose topic is also “communication-and-social” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
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.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- 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.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants 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
ssrfChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends 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; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks 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-dataChecks 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-boundaryChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks 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-hidingChecks 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-redirectChecks 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-deputyChecks 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
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks 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-validationChecks 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, 2026-10-23, 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.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,073 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 51 tools, 0 resources, 0 prompts.
- 4,270 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.
“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. “io.github.bluedotsoft/netsi: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.bluedotsoft/netsi
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
[](https://protocolprobe.com/mcp/servers/io.github.bluedotsoft/netsi)
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.
Write to hello@protocolprobe.com · corrections log · methodology