Skip to content

MCP servers › com.themethodic › candor

MCP server · registry snapshot 2026-11-19 · last tested 2026-11-19

candor MCP server

Registry name com.themethodic/candor

Candor UI docs — the publisher's title

by themethodic.com · domain (the registry's namespace rule)repository owner on GitHub: MethodicDev (organization)Source ↗Website ↗

Candor UI docs and component suggestions. Read-only, no key, never serves paid source. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-11-19version 6.11.0TypeScriptstreamable HTTP12 tools

Summary

com.themethodic/candor is a remote MCP server listed in the official MCP registry at version 6.11.0, under the namespace of the domain themethodic.com. Its linked repository is github.com/MethodicDev/candor; GitHub reports its owner as MethodicDev, an organization. On 2026-11-19 ProtocolProbe connected to it in read-only mode and read its inventory: 12 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  • not applicable: The version the registry lists can be installed and is not withdrawn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
12
Last tested
2026-11-19

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-19 (candor.themethodic.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 (6.11.0).

Add to your client

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-19
Mode
read-only (no tool calls)
Latest version
6.11.0, published 2026-11-18 (registry, as of the 2026-11-19 snapshot)
First listed version
2026-11-08 (earliest version still in the registry; older removed versions would be earlier)
Version history
38 versions listed, 2026-11-08 to 2026-11-18; 38 in the 90 days before the 2026-11-19 snapshot.
Most recent 12 versions
  • 6.11.0 · 2026-11-18
  • 6.8.1 · 2026-11-17
  • 6.8.0 · 2026-11-17
  • 6.7.0 · 2026-11-17
  • 6.2.2 · 2026-11-16
  • 6.2.0 · 2026-11-16
  • 6.1.3 · 2026-11-15
  • 6.1.0 · 2026-11-14
  • 6.0.0 · 2026-11-14
  • 5.4.0 · 2026-11-14
  • 5.3.0 · 2026-11-14
  • 5.2.0 · 2026-11-13
(versions still listed in the registry only)
Registry data
snapshot 2026-11-19
Package and repository
checked 2026-11-19
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

Version 6.8.1 (published 2026-11-17) → 6.11.0 (published 2026-11-18), between the registry lists of 2026-11-18 and 2026-11-19.

The publisher’s GitHub release note for v6.11.0 (“Candor 6.11.0”), published 2026-11-18.

Read the release note (the publisher’s text, shown as plain text, cut at 4,000 characters)
Released 2026-11-18.

Figures and meters: StatCard's quiet empty, label style and accent figure, PortfolioCard's count in its status line and a footer, RunLog grouped by hour with a footer the app fills, UsageMeter's dashed mark when no limit is set, and a success tone the app can choose for spend within its limit.

With no CLI or `@candor-ui/react` change: only Pro items and the docs change.

### Pro

- **StatCard and KpiRow take `labelStyle="strong"`,** the label at 11px, semibold, in the muted text colour. The
  default, `"default"`, is 12px regular, as before.
- **A `Kpi` takes `tone: "accent"`,** which draws its figure in the accent text colour, for the one figure the person
  acts on. The colour is emphasis only, and forced colours drop it: say in the label or `note` that it is waiting on
  the person ("Waiting on you"). A figure not computed, or with nothing yet, is drawn as it always is. The standard
  metrics card drops a model's `tone`, as it drops its `href`: which figure waits on the person is the app's to say.
- **A `Kpi` takes `empty`, with `value: null`,** for a metric with nothing to measure yet, such as an average with no
  runs. StatCard draws a small dash, hidden from screen readers, over your words, or "Nothing yet" with `empty: true`,
  and a screen reader hears those words in the figure's place. It is quiet, and never looks or reads like "Not
  computed", which stays the failure. `missing` wins over `empty`, since a failure must not read as calm, and a value
  wins over it; each logs a warning in development. A count of zero is `value: 0`. If you showed "None yet" through
  `notComputed` or `valueText`, move it to `empty`. The standard metrics card drops a model's `empty`, so a model's
  null still reads "Not computed": only the app knows there is nothing to measure.
- **PortfolioCard takes `needsYouPlacement="status"`,** which puts the count of things that need the person at the end
  of the status line, in words after the locale's separator ("On hold · 2 need you"), with no chip, for a card held on
  purpose. The count is still shown and read; zero follows `allClear`, and "Not checked" is always shown. The default,
  `"chip"`, is as before.
- **PortfolioCard takes `footer`,** one line of your words under everything else on the card ("Paused at stage 3, 14
  Nov"), drawn as plain text in an isolate. It is a string, not a slot, since the card is one link.
- **RunLog takes `heading`:** a string in place of "Runs", or `false` for a page whose own heading names the log. The
  log keeps its name for screen readers either way, and with `false` its header row is left out when nothing else is in
  it (no `toolbar`, status filter, or Export once the runs are known). Blank words are no heading: the log reads "Runs".
- **RunLog takes `groupBy="hour"`,** which puts the runs under a heading for the hour they started, in
  LocaleProvider's time zone and date format, newest first, each heading with how many runs it holds ("6 Nov 2026,
  14:00 (3 runs)"). Before the page hydrates the hours are UTC's and say so, as every time in the log is, unless the
  provider sets both a locale and a time zone. An hour is the hour on the clock, in a zone a half or three quarters of
  an hour off UTC too; where the clocks go back and two hours read the same, each says its offset ("25 Oct 2026, 01:00
  GMT+1"). While RunLog's own status filter is on Failed or Running, a heading counts the runs shown ("1 shown"). A
  run whose start time can't be read goes under "Time not known", last unless `groupOrder` names it (`""`).
  `groupBy` also takes a function that returns each run's own key, with `groupOrder` and `groupLabel`, as
  DataTable's; a run it gives no key, or a group `groupLabel` gives no words, is under "No group", and an empty key
  logs a warning in development. With `"hour"`, a key in `groupOrder` is the hour's start as a time, matched by its
  moment however it is written.
- **RunLog lists the runs newest first by the moment e

The release on GitHub

Source: the official MCP Registry list on 2026-11-18 and on 2026-11-19; release notes from the GitHub Releases API, checked 2026-11-19.

What it is

What does this server offer?

Observed inventory
12tools
0resources
0prompts

None of its 12 tools are described as changing anything. For 12 the reading was uncertain, so no mark is shown.

  • “Search Candor UI's components, hooks, blocks and patterns by what they do ("approve a tool call", "cost estimate", "session list").”

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

    3 inputs, 1 required
    • querystringrequired“What you're looking for, in words.”
    • tierstring“Only items this tier unlocks: free, pro (free and Pro) or premium (everything).”
    • limitinteger“At most this many items (default 10).”
  • get_component_docson 1 other server

    “Read one item's docs as Markdown: what it is, its tier and install command, an example with the import paths an app uses, every prop, function, type, and the LocaleProvider string keys.”

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

    2 inputs, 1 required
    • namestringrequired“The registry name, e.g.”
    • versionstring“A release, e.g.”
  • suggest_components

    “Describe the screen or feature you're building; get the Candor UI items that fit, why, the matching patterns and screens, and an install command per tier.”

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

    3 inputs, 1 required
    • taskstringrequired“What you're building, e.g.”
    • tierstring“Only suggest what this tier unlocks.”
    • sdkstring“The agent SDK the app uses: ai-sdk (the Vercel AI SDK), claude (the Claude Agent SDK) or ag-ui.”
  • list_componentson 46 other servers

    “List every item by group (Chat, Agent work, App shell, …; the app scaffolding groups, Layout, Charts, Team, Billing and Admin, after the agent groups), or one group's items with descriptions.”

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

    2 inputs
    • groupstring“A group's title, e.g.”
    • tierstring“Only items this tier unlocks.”
  • “Read a pattern as Markdown: a common problem in agent UIs (approvals, traces, cost guards, …) and the components that solve it.”

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

    2 inputs, 1 required
    • slugstringrequired“The pattern's slug, as search_docs or suggest_components gives it.”
    • versionstring“A release, e.g.”
  • list_screenson 3 other servers

    “List the screen catalogue by area (talking to the agent, approving and controlling, watching the work, …), one line per screen: what it's for and its slug.”

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

    1 input
    • areastring“An area's title, e.g.”
  • “Read one screen as Markdown: what it's for, two or three layouts with when to pick each, the Candor UI items that build each (with tiers), an install command, the honesty rules that matter most on it…”

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

    2 inputs, 1 required
    • slugstringrequired“The screen's slug, as list_screens or suggest_components gives it, e.g.”
    • versionstring“A release, e.g.”
  • “How to install Candor UI in a React or Next.js app, render a chat, connect an agent SDK, add licensed items and keep them updated.”

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

    2 inputs
    • promptboolean“true: only the adoption prompt, to hand to a coding agent.”
    • versionstring“A release, e.g.”
  • “One item's brief to hand to the coding agent that builds the screen: the same Markdown the docs page's "Copy for a coding agent" button copies (what the item is, its tier and install command, an exam…”

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

    2 inputs, 1 required
    • namestringrequired“The registry name, e.g.”
    • versionstring“A release, e.g.”
  • “The design system as Markdown: every colour role and what it's for, the type scale, radius, shadows, motion, density and themes, read from the shipped CSS; how an app re-tokens for its brand; and how…”

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

    1 input
    • versionstring“A release, e.g.”
  • get_review_checklist

    “The checklist to run after each screen where an AI agent acts, before moving on: one line per check, each tied to a rule (model output is text, unknown stays unknown, a locked control says why, nothi…”

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

    1 input
    • versionstring“A release, e.g.”
  • theme_check

    “Check a brand file (candor-brand.css, or any CSS that sets Candor's tokens) the way `npx candor-ui theme check` does: colour contrast of every text and edge pairing in light, dark and high contrast, …”

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

    2 inputs, 1 required
    • cssstringrequired“The CSS to check: the whole text of candor-brand.css (at most 256 KB).”
    • filenamestring“What to call it in findings (default candor-brand.css).”

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 2026-11-19.

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
100% of 23
Tools with a description
100% of 12
Typical description length
405 characters

The tool set

Counted from the listing

Tools
12
Size of the list
about 3,231 tokens for an agent to load (characters ÷ 4)
Naming
12 of 12 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 12 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. 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 2026-11-19 (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://candor.themethodic.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "candor": {
      "url": "https://candor.themethodic.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "candor": {
      "type": "http",
      "url": "https://candor.themethodic.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"candor","type":"http","url":"https://candor.themethodic.com/mcp"}'
Claude Code
claude mcp add --transport http candor https://candor.themethodic.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "candor": {
      "type": "streamableHttp",
      "url": "https://candor.themethodic.com/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "candor": {
      "httpUrl": "https://candor.themethodic.com/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.candor]
url = "https://candor.themethodic.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "candor": {
      "url": "https://candor.themethodic.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://candor.themethodic.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 2026-11-19. 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 2026-11-19. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-19. Source: read 2026-11-19.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-19. Source: read 2026-11-19.

Own host

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 candor.themethodic.com/mcpSession openedmatchesour test · 2026-11-19
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-19
Repository github.com/MethodicDev/candorOpens publiclymatchesapi.github.com · 2026-11-19

Who made it?

Feature #7 · lineage

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

Namespace
com.themethodic
GitHub owner
an organization (MethodicDev)
Repository
github.com/MethodicDev/candor
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 · 2026-11-19; security policy read from GitHub · 2026-11-08.

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.

Tool list changes

Our reads compared · no tool called

Hosted endpoint candor.themethodic.com/mcp

5 of 9 comparisons between consecutive reads showed a change (10 reads, 2026-11-08 to 2026-11-19; versions 2.1.0 to 6.11.0).

Last change seen between our reads on 2026-11-15 (version 6.1.0) and 2026-11-16 (version 6.2.2).

Removed (1):

item_changes

Changed (7):

get_brief: input schemaget_component_docs: input schemaget_design: input schemaget_pattern: input schemaget_review_checklist: input schemaget_screen: input schemaget_started: input schema

No change in the 3 reads since (to 2026-11-19).

Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-19 is not known yet. No tool was called. How it is compared

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 2026-11-19 (security policy 2026-11-08). 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.themethodic/candor

Answered from the data above

Who publishes com.themethodic/candor?

The registry ties the namespace com.themethodic to the domain themethodic.com; only its owner can publish under it. Its linked repository is github.com/MethodicDev/candor; GitHub reports its owner as MethodicDev, an organization. These are facts from the registry and GitHub, not a rating.

Is com.themethodic/candor 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.themethodic/candor need an API key or sign-in?

It opened a session without any credential on 2026-11-19. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.themethodic/candor been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its 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). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Does com.themethodic/candor 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.themethodic/candor?

In github.com/MethodicDev/candor, 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

Not probed (no operator permission)

We connected and read what the server declares, but did not call its 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). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-19
  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: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 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 · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.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 · 4
  • 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
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-11-19, 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. 743 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 12 tools, 0 resources, 0 prompts.
  4. 4,090 msFinished: 2 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 2026-11-19; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
api.github.com · 2026-11-19
Hosting type
registry · 2026-11-19
MCP capability
tools
our test · 2026-11-19
Transport
streamable HTTP
registry · 2026-11-19
Required credentials
none declared
registry · 2026-11-19 · 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 · 2026-11-19
Lifecycle status
registry · 2026-11-19
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: an organization · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-11-19
Maintenance
api.github.com · 2026-11-19
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-19

“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.themethodic/candor: MCP server record.” Data checked 2026-11-19. https://protocolprobe.com/mcp/servers/com.themethodic/candor

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.themethodic/candor)](https://protocolprobe.com/mcp/servers/com.themethodic/candor)

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