MCP servers › us.srv.g5joilnmeep4ntz3nwezxt5dmu › stackfacts

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts

Signed EOL dates, exploited CVEs and LLM prices; pay per call in USDC, no account, no daily cap. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedPricing: freemium · AI-classifiedversion 0.5.0streamable HTTP41 tools

Summary

us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts is a remote MCP server listed in the official MCP registry at version 0.5.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 41 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

met: Registry entry is active and says how to run it
not met: Source repository link opens
not applicable: Repository is not archived
not applicable: Code pushed to the repository in the 90 days before our check
not applicable: 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not applicable: The version the registry lists can be installed and is not withdrawn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: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Tools: 41
Described as changing data: 0 of 41 toolsAI-classified
Mainly works on: nothing outside itself: it only answers questionsAI-classified
Topic: developer-toolsAI-classified
Pricing: freemiumAI-classified
Last tested: 2026-10-23

Add to your client

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: 0.5.0, published 2026-10-12 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-12 (earliest version still in the registry; older removed versions would be earlier)
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 0.5.0 (published 2026-10-12).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

41tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 41 tools are described as changing anything. For 1 the reading was uncertain, so no mark is shown.

stackfacts_eol_productreads or searches
“List every release cycle of a product (Node.js, Python, Ubuntu…) and if it is still supported: EOL (end-of-life) date, support status, LTS, latest version.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- productstringrequired“endoflife.date product id or alias, e.g.”
stackfacts_eol_cyclereads or searches
“Check if a version is still supported (is python 3.12 still supported?): one release cycle, its EOL (end-of-life) date, support status, LTS, latest patch.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- productstringrequired“endoflife.date product id or alias, e.g.”
- cyclestringrequired“Release cycle, e.g.”
stackfacts_eol_checkreads or searches
“Check runtimes and OS versions for EOL: is each still supported?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- itemsarrayrequired“The versions to check, in order”
stackfacts_eol_imagereads or searches
“Check a container image for EOL: is node:18-alpine still supported?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- imagestringrequired“Image reference or a whole Dockerfile FROM line (FROM, --platform and AS name are dropped), e.g.”
stackfacts_eol_snapshotreads or searches
“Download the signed EOL (end-of-life) snapshot (endoflife.date, MIT): support status of every product and cycle, still supported or not, plus its manifest.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
stackfacts_kev_lookupreads or searches
“Check if a CVE is actively exploited (CISA KEV): in_kev, date added, remediation due date, required action and known ransomware use.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- cvestringrequired“CVE id, e.g.”
stackfacts_kev_checkreads or searches
“Check up to 100 CVEs at once against CISA KEV (known exploited vulnerabilities); returns in_kev and the KEV details for each one.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- cvesarrayrequired“CVE ids; duplicates are merged”
stackfacts_kev_changesreads or searches
“List CVEs added to, removed from or changed in CISA KEV since a snapshot_id, so an agent can poll for newly exploited vulnerabilities.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- sincestringrequired“meta.snapshot_id of an earlier kev answer, e.g.”
stackfacts_kev_snapshotreads or searches
“Download the full signed CISA KEV snapshot: every known exploited vulnerability, with a manifest to verify the sha256 and signature.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
stackfacts_models_lookupreads or searches
“Get an LLM model's price per million tokens (input, output, cached), context window, max output, capabilities and model deprecation date.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- providerstringrequired“Provider, e.g.”
- modelstringrequired“Model id at the provider, e.g.”
stackfacts_models_estimatecalculates or converts
“Estimate the USD cost of an LLM call from input, output and cached token counts, exact to the micro-dollar, with the price lines used.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- modelstringrequired“provider/model id, e.g.”
- input_tokensinteger“Uncached input tokens”
- output_tokensinteger“Output tokens”
- cached_tokensinteger“Cached input tokens (cache reads)”
stackfacts_models_cheapestreads or searches
“Find the cheapest model with tools and 128k context, or any limits you set: ranks the 10 cheapest LLMs by blended price per million tokens.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- min_contextinteger“Minimum context window in tokens”
- toolsboolean“Require tool calling”
- visionboolean“Require image input”
- max_usd_per_mtoknumber“Max blended USD per million tokens (3:1 input:output)”
- providersarray“Only these providers”
- include_deprecatedboolean“Keep deprecated models (default false)”
- include_freeboolean“Keep models priced 0/0 (default false)”

Show 29 more tools

stackfacts_models_changesreads or searches
“List LLM models added, removed or changed (price per million tokens, context window, model deprecation date) since a snapshot_id.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- sincestringrequired“meta.snapshot_id of an earlier models answer, e.g.”
stackfacts_models_watchreads or searches
“Check LLMs for what changed since your last call: changed records (with today's price and limits), removals, deprecated or soon deprecated, with snapshot dates.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- modelsarrayrequired“provider/model ids, e.g.”
- sincestring“meta.snapshot_id of your last answer; omit on the first call”
- warn_daysinteger“Alert when deprecation is this many days away or less (default 90)”
stackfacts_models_snapshotreads or searches
“Download the full signed LLM model catalogue (LiteLLM + models.dev, MIT): prices, limits and capabilities, with a verifiable manifest.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
stackfacts_stack_checkreads or searches
“Check dependencies, runtimes and OS versions in one call: OSV for up to 50 purls, EOL for 50 product@version pairs, CISA KEV hits, suggestions for unknowns.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- itemsarray“The versions to check, in order: "product@version" strings or {product, version} objects.”
- cvesarray“Optional CVE ids to check against CISA KEV; duplicates are merged.”
- packagesarray“Optional package URLs with versions, answered as POST /v1/osv/check answers them (advisories, fixed versions, KEV flag).”
stackfacts_osv_checkreads or searches
“Check dependencies or a lockfile for vulnerable and malicious packages: up to 50 purls, or a package-lock, yarn.lock, requirements.txt or poetry.lock, on OSV.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- packagesarray“Package URLs with versions, in order.”
- lockfilestring“Instead of packages: the text of a package-lock.json, yarn.lock (v1), requirements.txt or poetry.lock; its distinct exact versions are checked (at most 50).”
- formatstring“The lockfile's format; detected when left out”
stackfacts_preflightreads or searches
“Call before installing a package an LLM suggested: one npm, PyPI or purl version against OSV, CISA KEV and EOL data.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- packagestring“Package URL with a version, e.g.”
- ecosystemstring“npm, pypi, golang, cargo or maven (with name and version, instead of package)”
- namestring“Package name as the registry spells it, e.g.”
- versionstring“Exact version, e.g.”
stackfacts_cve_lookupreads or searches
“Get any CVE: CISA KEV entry, CVSS score and patch priority, plus every OSV advisory aliased to it, with affected packages and fixed versions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“CVE id, e.g.”
stackfacts_cwe_lookupreads or searches
“Get one MITRE CWE weakness by id (79 or CWE-79): name, status, description and MITRE link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“CWE id, e.g.”
stackfacts_technique_lookupreads or searches
“Get one technique by id (T1055.011): name, tactics, platforms, description, mitigations, detection, data sources and link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Technique id, e.g.”
stackfacts_capec_lookupreads or searches
“Get one MITRE CAPEC attack pattern by id: severity, likelihood, prerequisites, mitigations, related CWE and ATT&CK ids and MITRE link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“CAPEC id, e.g.”
stackfacts_domain_lookupreads or searches
“Get the public suffix, registrable domain and subdomain of a host name from the Mozilla Public Suffix List, with the matching rule and section.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- hoststringrequired“Host name, e.g.”
stackfacts_port_lookupreads or searches
“Get the IANA service name, transport, description and reference for a port number from the IANA Service Name and Transport Protocol Port Number Registry.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- numberstringrequired“Port number from 0 to 65535, e.g.”
stackfacts_control_lookupreads or searches
“Get one NIST SP 800-53 Rev 5 security control or enhancement by id (AC-2, AC-2(1)): title, statement, guidance, related controls and status.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Control id like AC-2 or enhancement AC-2(1) (ac-2.1 also works)”
stackfacts_bcp47_lookupreads or searches
“Get an IANA language tag (en-AU, zh-Hant) part by part: type, description, scope, deprecation and preferred value from the Language Subtag Registry.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- tagstringrequired“IANA language tag like en, en-AU or zh-Hant (case does not matter)”
stackfacts_tz_lookupreads or searches
“Get an IANA time zone (Europe/Berlin) or alias: current UTC offset, abbreviation, DST summary and backward-compatible names from tzdata.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- zonestringrequired“IANA time zone like Europe/Berlin, UTC or an alias such as US/Pacific (case does not matter; a path needs the slash sent as %2F)”
stackfacts_package_cardreads or searches
“Get an npm or PyPI package's latest version, publish dates, deprecation or yank, SPDX licence, repository and runtime range.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- ecosystemstringrequired“npm or pypi”
- namestringrequired“Package name, e.g.”
- versionstring“Version to describe (npm: or a dist-tag); default the latest”
stackfacts_license_checkreads or searches
“Call before adding a dependency: check SPDX licences or packages against your project licence and use, with a compatibility verdict per item.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- itemsarrayrequired“Up to 20 items: an SPDX licence expression (MIT, GPL-2.0-or-later, MIT OR Apache-2.0) or a package with its declared licence; a package with no licence is unkn…”
- project_licensestring“Your project's licence: one SPDX id (Apache-2.0, GPL-3.0-only) or proprietary; default proprietary”
- usestring“How you ship it: distribute (default), saas (network use only) or internal”
stackfacts_cve_prioritizereads or searches
“Call before patching: rank up to 100 CVEs by CISA KEV status, then CVSS base score.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- cvesarrayrequired“Up to 100 CVE ids, e.g.”
stackfacts_cve_searchreads or searches
“Find CVEs by keyword or package name in CISA KEV and OSV (not all of NVD), with KEV status and CVSS v3 where an OSV advisory has one.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- qstring“Keyword search (send q or package, not both): 1 to 8 words, all must appear in the CISA KEV vendor, product or vulnerability name; also tried as an exact OSV p…”
- packagestring“Package name (send q or package, not both), matched exactly in the OSV advisories, e.g.”
- ecosystemstring“With package only: npm, PyPI, Maven, Go, crates.io, NuGet, RubyGems or Packagist (or the purl type); default all”
- kevboolean“true: only CVEs in CISA KEV; false: only CVEs not in KEV”
- severitystring“Only CVEs of this severity or higher (from the OSV advisories; keeps only CVEs with an OSV score or label, so most KEV-only CVEs are left out)”
- limitinteger“Most results to return (default 20, at most 50)”
stackfacts_package_preflightreads or searches
“Call before installing an npm or PyPI package: latest or given version, licence, OSV vulns, CISA KEV CVEs, deprecation or yank.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 2 required
- ecosystemstringrequired“npm or pypi”
- namestringrequired“Package name, e.g.”
- versionstring“The version to judge: an exact version (e.g.”
- project_licensestring“Your project licence, one SPDX id (e.g.”
- usestring“How the package is used: distribute (default), saas or internal”
stackfacts_upgrade_deltareads or searches
“Check moving an npm or PyPI package from one version to another: advisories fixed or introduced, KEV, licence, runtime.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 3 required
- ecosystemstringrequired“npm or pypi”
- namestringrequired“Package name, e.g.”
- fromstringrequired“The version you run now: an exact version or an npm dist-tag”
- tostring“The version you move to; default the latest.”
- project_licensestring“Your project licence, one SPDX id (e.g.”
- usestring“How the package is used: distribute (default), saas or internal”
stackfacts_lockfile_diffreads or searches
“Check npm or PyPI purl lists or raw lockfiles: upgrades judged on advisories, KEV, licence; same version, other hash = hash_mismatch.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- fromarray“Packages before, as purls with a version, e.g.”
- toarray“Packages after, as purls with a version (or {purl, integrity}); a package in both lists at another version is judged, one in a single list is reported added or…”
- from_lockfilestring“Instead of from: the text of a package-lock.json, yarn.lock, requirements.txt or poetry.lock (1 MB at most; the whole body 2.5 MB).”
- to_lockfilestring“Instead of to: the text of a package-lock.json, yarn.lock, requirements.txt or poetry.lock (1 MB at most).”
stackfacts_stack_watchreads or searches
“Check dependencies, runtimes and OS versions for what changed since your last call: EOL passed or near, new OSV advisories, new CISA KEV hits.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- itemsarray“The versions to check, in order: "product@version" strings or {product, version} objects.”
- cvesarray“Optional CVE ids to check against CISA KEV; duplicates are merged.”
- packagesarray“Optional package URLs with versions, answered as POST /v1/osv/check answers them (advisories, fixed versions, KEV flag).”
- warn_daysinteger“Start only: report an item as due soon when its EOL date is this many days away or fewer (default 90, 0 = off).”
- tokenstring“Re-check only: data.watch.token from your last answer.”
- fullboolean“Re-check only: also return data.check, the full current stack answer, at the same price (default false)”
stackfacts_previewreads or searches
“Preview a dataset for free: sample end-of-life products, newest CISA KEV entries, LLM prices, a package card or a licence verdict.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- datasetstringrequired“Dataset: eol (software end-of-life), kev (CISA known exploited vulnerabilities), models (LLM prices), package (npm/PyPI package card) or license (licence compa…”
stackfacts_tryreads or searches
“Try a paid answer for free on a fixed example: nodejs end-of-life cycles, CVE-2021-44228 in CISA KEV, or openai/gpt-4o prices.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- datasetstringrequired“Dataset: eol (software end-of-life), kev (CISA known exploited vulnerabilities) or models (LLM prices)”
stackfacts_indexreads or searches
“List the valid ids for free: end-of-life product names and aliases, or LLM provider/model ids, so a paid call never misses.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- datasetstringrequired“eol (product ids and aliases) or models (provider/model ids)”
stackfacts_validatereads or searches
“Validate an id for free.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- datasetstringrequired“Dataset: eol (software end-of-life), kev or cve (CISA known exploited CVEs; cve is kev), models (LLM prices), cwe (MITRE CWE), technique (MITRE ATT&CK) or cape…”
- idstringrequired“Id to check: nodejs, nodejs/22, CVE-2021-44228, openai/gpt-4o, CWE-79, T1059 or CAPEC-66”
stackfacts_manifestreads or searches
“Get the signed manifest of a dataset's latest snapshot for free: snapshot_id, sha256, record count, source, licence and signature.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- datasetstringrequired“Dataset: eol (software end-of-life), kev (CISA known exploited vulnerabilities) or models (LLM prices)”
stackfacts_keys
“Get the Ed25519 public keys (JWK) that verify the signature on every answer and snapshot manifest.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.

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: 100% of 40 tools
States limits, defaults or errors: 0% of 39 tools
Says when to use it: 0% of 40 tools
Items covered per tool: 2.0 of 4 on average

Counted from the listing

Parameters with a description: 100% of 84
Tools with a description: 100% of 41
Typical description length: 141 characters

The tool set

Counted from the listing

Tools: 41
Size of the list: about 11,331 tokens for an agent to load (characters ÷ 4)
Naming: 41 of 41 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 40 of 41 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://g5joilnmeep4ntz3nwezxt5dmu.srv.us/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "stackfacts": {
      "url": "https://g5joilnmeep4ntz3nwezxt5dmu.srv.us/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "stackfacts": {
      "type": "http",
      "url": "https://g5joilnmeep4ntz3nwezxt5dmu.srv.us/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"stackfacts","type":"http","url":"https://g5joilnmeep4ntz3nwezxt5dmu.srv.us/mcp"}'

Claude Code

claude mcp add --transport http stackfacts https://g5joilnmeep4ntz3nwezxt5dmu.srv.us/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://g5joilnmeep4ntz3nwezxt5dmu.srv.us/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 #6

The 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 g5joilnmeep4ntz3nwezxt5dmu.srv.us/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

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
Not metSource repository link opensThe registry entry gives no repository link.
Does not applyRepository is not archivedNo public GitHub repository to read.
Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
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 us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts

Answered from the data above

Is us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts free to use?

Its website (g5joilnmeep4ntz3nwezxt5dmu.srv.us/docs/mcp) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts 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 us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts 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. This is our choice, not a block by the server. No security verdict is published before verification.

What can us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts do?

It lists 41 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 and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts change or delete data?

None of its 41 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.

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.

Similar servers

Same topic · AI-read

io.github.revolist/revogrid-mcp-proRevoGrid DataGrid MCP Proalso has tools that calculates or converts, reads or searchescompare with this one
io.github.SceneView/mcpalso has tools that calculates or converts, reads or searchescompare with this one
io.github.ThomasGorisse/sceneviewalso has tools that calculates or converts, reads or searchescompare with this one
io.github.sceneview/mcpalso has tools that calculates or converts, reads or searchescompare with this one
io.github.Vrun-design/openflowkit-mcpalso has tools that calculates or converts, reads or searchescompare with this one
io.github.openflowkit/openflowkit-mcpalso has tools that calculates or converts, reads or searchescompare with this one

Active servers whose topic is also “developer-tools” 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

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. 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 · 2026-10-23

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: 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.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 12

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

Does not apply to this server · 4

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
18Sign-in metadata
oauth-url-schemeChecks 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, 2026-10-23, 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
2,844 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 41 tools, 0 resources, 0 prompts.
10,559 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

developer-tools

AI-classified · 2026-10-23

Pricing modelAI-classified

freemium

read from g5joilnmeep4ntz3nwezxt5dmu.srv.us/docs/mcp · 2026-10-23

“Free tools answer in the client: stackfacts preview, stackfacts try, stackfacts index, stackfacts validate, stackfacts manifest, stackfacts keys.”

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · 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 · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

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

not stated

no readable GitHub owner to describe

Maintenance

does not apply

server declares no repository link, so there is nothing to fetch

Environment

the publisher's infrastructure

where it runs, from the hosting type

“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. “us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts

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](https://protocolprobe.com/api/v1/badge/us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts)](https://protocolprobe.com/mcp/servers/us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts)

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