Skip to content

MCP servers › works.narrate › public

MCP server · registry snapshot 2026-11-12 · last tested 2026-11-14

public MCP server

Registry name works.narrate/public

Narrate — the publisher's title

by narrate.works · domain (the registry's namespace rule)Website ↗

Narrate's public knowledge on impact management, for your AI assistant. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-14version 1.0.0streamable HTTP37 tools

Summary

works.narrate/public is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain narrate.works. On 2026-11-14 ProtocolProbe connected to it in read-only mode and read its inventory: 37 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  • not applicable: The version the registry lists can be installed and is not withdrawn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

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
Tools
37
Last tested
2026-11-14

Tool list size

13,469 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (37 tools). Counted with Anthropic's token counter on 2026-11-14, from the tool list we read on 2026-11-14. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-14 (narrate.works), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.0.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 1 tool whose name or declaration suggests it changes data (presentation_save_answer). That is our reading of the names; we did not call it. Source: our connection, 2026-11-14.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-14
Mode
read-only (no tool calls)
Latest version
1.0.0, published 2026-11-10 (registry, as of the 2026-11-12 snapshot)
First listed version
2026-11-10 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-11-12
Package and repository
checked 2026-11-12
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. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-09, listed on 2026-11-12 with version 1.0.0 (published 2026-11-10).

Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12.

What it is

What does this server offer?

Observed inventory
37tools
0resources
0prompts

None of its 37 tools are described as changing anything. For 37 the reading was uncertain, so no mark is shown.

  • get_code_list

    “The reference lists Narrate keeps (narrate.works/naslag/lijsten), with each code's name in Dutch or British English.”

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

    3 inputs
    • liststring“Which list, such as countries, currencies, sdg, nace or six-capitals.”
    • querystring“Part of a code or name to filter on, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • search_glossaryon 13 other servers

    “Search the words Narrate uses for impact management (begrippen), in Dutch or English.”

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

    2 inputs, 1 required
    • querystringrequired“A word or phrase, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • get_glossary_termon 13 other servers

    “Everything about one word of the Narrate glossary by its id (from search_glossary): the term in both languages, its definition per language level, the words to avoid, an example, the words not to con…”

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

    1 input, 1 required
    • idstringrequired“The stable id, e.g.”
  • “Search the public pages of narrate.works (articles, guides, materials, the glossary) by title, description and full text.”

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

    2 inputs, 1 required
    • querystringrequired“Words to look for in the title, the description or the text.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “Reads one public page of narrate.works as Markdown, opening with that page's instructions for AI assistants (how to cite it, what not to say).”

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

    1 input, 1 required
    • pathstringrequired“The site path, starting with '/'.”
  • search_sourceson 13 other servers

    “Search the sources Narrate cites (reports, laws, standards, books, our own counts) by title, publisher or id.”

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

    2 inputs, 1 required
    • querystringrequired“Words to look for in the title or publisher, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “Everything public about one source by its id (from search_sources): title, publisher, date, URL, licence, the literal quote Narrate leans on and where it stands, whether it was checked three times, a…”

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

    2 inputs, 1 required
    • idstringrequired“The stable id, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “The links of one glossary word or one source in Narrate's reference work (Maktoob), both ways, each with its open-standard name: broader and narrower (skos:broader, iso-thes:broaderPartitive), relate…”

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

    2 inputs, 2 required
    • kindstringrequired“term for a glossary word, source for a source.”
    • idstringrequired“The stable id, e.g.”
  • search_keywordson 2 other servers

    “The keywords Narrate tags its work with, by group: perspectives, phases, challenges, sectors, organisational forms, frameworks, technology and product forms.”

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

    2 inputs, 1 required
    • querystringrequired“A word to look for, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • list_articleson 70 other servers

    “Narrate's published articles, newest first, as on narrate.works/materialen/artikelen (English /resources/articles).”

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

    4 inputs
    • formstring“Only the articles of this form (category).”
    • querystring“Words to look for in the title or description.”
    • limitinteger“How many articles, newest first.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “How Narrate's services stand right now (website, signing in, data, workspace: working, slow or disrupted), the notice that is open, and planned maintenance within a day.”

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

    1 input
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • list_specials

    “The specials: Narrate's long, illustrated articles, with figures you can explore.”

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

    2 inputs
    • querystring“Words to look for in the title or description.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
Show 25 more tools
  • suggest_examples

    “Narrate's example library: made-up initiatives that explain an idea in the reader's own world.”

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

    5 inputs
    • audiencestring“The audience group, such as sportsClubs or municipalities.”
    • challengestring“The societal challenge, such as energietransitie or kansengelijkheid.”
    • nacestring“A NACE Rev.”
    • countinteger“How many, one to five.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • list_exampleson 19 other servers

    “Every made-up example in Narrate's library that matches all given filters, in library order, each as a short card: situation, the change they want, the rights-holders, one figure and what is hard abo…”

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

    5 inputs
    • audiencestring“Only examples this audience group recognises.”
    • challengestring“Only examples about this challenge.”
    • nacestring“Only examples in this NACE section.”
    • scalestring“Only examples at this scale.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “One made-up example by its id (from suggest_examples or list_examples): its card, the audience groups it serves and its tags.”

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

    2 inputs, 1 required
    • idstringrequired“The example's id, such as repaircafe.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • example_coverage

    “Per audience group: how many made-up examples it has, how many the group would run itself and over how many challenges they spread, against the norm of the library.”

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

    1 input
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • get_audience_fields

    “The societal challenges and sectors where Narrate did work for one audience group, taken only from the cases and clients its own page shows.”

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

    2 inputs, 1 required
    • audiencestringrequired“The group: its key or the last part of its address, e.g.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • suggest_changeon 1 other server

    “Hand Narrate's team a suggestion without an account: a correction to a page or a glossary word, a missing source, an idea.”

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

    3 inputs, 2 required
    • subjectstringrequired“What it is about, in a few words: a page path, a glossary word, 'the source register'.”
    • bodystringrequired“What should change, and why.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • request_beta_accesson 1 other server

    “Ask to join the beta of the Fabrik apps (iPhone, iPad, Android) for a person, without an account: their email address, and if they like their name, organisation, the platforms they use and a short no…”

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

    7 inputs, 1 required
    • emailstringrequired“The person's own email address, where the invitation goes.”
    • namestring“Their name.”
    • organizationstring“The organisation they work for or with.”
    • platformsarray“Where they would use it: ios (iPhone and iPad), android, web.”
    • notestring“What they would like to use it for.”
    • viastring“Where the request comes from: the site's form, the app, or an assistant (the default).”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • list_shop_catalog

    “The products and services in Narrate's shop, as narrate.works/winkel (English /shop) shows them: name, description, price excluding VAT (null is price on request), billing frequency, thumbnail and wh…”

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

    1 input
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • get_quote_request_form

    “One product of Narrate's shop that ends in a quote, with the questions the request form asks (each with its options, or the range for a number) and the page where the person fills it in.”

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

    2 inputs, 1 required
    • product_idstringrequired“The product's id, from list_shop_catalog.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • terms_which_apply

    “Which of Narrate's terms apply to what an organisation takes from Narrate, as the helper on narrate.works/over/juridisch/voorwaarden (English /about/legal/terms) shows.”

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

    3 inputs
    • documentsarray“Slugs of the documents chosen, from `choices`.”
    • personal_databoolean“Narrate processes personal data for the organisation.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • get_quote_to_sign

    “The quote Narrate sent to sign, opened with the key from the signing link (narrate.works/offerte-tekenen#<key>, English /sign-quote): number, title, the lines and terms, the proposal, who is expected…”

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

    2 inputs, 1 required
    • keystringrequired“The key from the link (the part after #, 43 characters).”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • start_quote_signing

    “Starts signing the quote behind the key at Signhost, Narrate's signing service: give the signer's name, job title and e-mail address, and send the person to the url it returns, where they sign themse…”

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

    5 inputs, 3 required
    • keystringrequired“The key from the link (the part after #, 43 characters).”
    • namestringrequired“The signer's full name.”
    • job_titlestring“The signer's job title.”
    • emailstringrequired“The signer's e-mail address: Signhost sends the signed quote there.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • get_client_evaluation_form

    “The evaluation form a client of Narrate got by mail (narrate.works/klantevaluatie#<key>), opened with the key from that link: which moment (midway or final), the track and organisation, when it opens…”

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

    2 inputs, 1 required
    • keystringrequired“The key from the link (the part after #, 43 characters).”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • submit_client_evaluation

    “Sends the client's answer to the evaluation behind the key, or changes it, while the moment is open: ratings and texts per question id, and an optional quote with the consent to use it (none, anonymo…”

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

    3 inputs, 2 required
    • keystringrequired“The key from the link (the part after #, 43 characters).”
    • answerobjectrequired“The answer, per question id as get_client_evaluation_form's moment asks it.”
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • presentation_sign_up

    “Sign a phone up for a live session of Narrate, by the room code on the presenter's screen: the person's name, email address and initiative, the version of the terms they agreed to, and whether they w…”

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

    11 inputs, 6 required
    • codestringrequired“The room code on the presenter's screen, such as FCA6.”
    • participantstringrequired“The phone's own random id, the same for every call from it.”
    • presentationstringrequired“The presentation's slug, as the screen shows it.”
    • sessionstring“The session's id, if the phone knows it.”
    • partnerstring“The partner of the session, if any.”
    • namestringrequired“The person's name.”
    • emailstringrequired“Their email address (the same rough check as the database).”
    • initiativestring“The initiative they take part for.”
    • terms_versionstringrequired“The version of the terms they agreed to.”
    • create_userboolean“Whether they asked for an account.”
    • beta_versionstring“The beta terms they agreed to, if any.”
  • presentation_save_answer

    “Save a phone's answer to a slide of a live session it signed up for (presentation_sign_up): a choice, a point on a scale or a line of text.”

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

    5 inputs, 5 required
    • idstringrequired“The answer's own id, made by the phone.”
    • codestringrequired“The room code on the presenter's screen, such as FCA6.”
    • participantstringrequired“The phone's own random id, the same for every call from it.”
    • slidestringrequired“The slide's id.”
    • valuestring or numberrequired“The answer: the chosen option ids, a number or text.”
  • presentation_read_live

    “Read where the presenter's screen of a live session is, by its room code: the state the screen keeps (the presentation, the slide, a running timer) and how many milliseconds ago it was set.”

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

    1 input, 1 required
    • codestringrequired“The room code on the presenter's screen, such as FCA6.”
  • list_parties

    “Every organization in Narrate's public landscapes, each once with its roles: funder (the funding landscape: public schemes, funds, foundations, impact investors, banks), impact_organization (the impa…”

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

    2 inputs
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
    • rolestring“Only the parties with this role: funder, impact_organization or accelerator.”
  • list_indicatorson 15 other servers

    “Every indicator in Narrate's indicator catalogue (narrate.works/naslag/indicatoren): its name and definition in Dutch and English, the unit, the layer (input to impact), the domain, the SDG it measur…”

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

    1 input
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • “Every metric in Maktoob, Narrate's reference work (narrate.works/naslag/metrics): what you measure, apart from any goal.”

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

    1 input
    • langstring“Language of the text and the answer: nl (Dutch) or en (British English).”
  • list_framework_origins

    “Narrate's herkomst list: where the frameworks, standards and methods of the impact field come from.”

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

    1 input
    • liststring“Only the records of this list.”
  • get_reference_settings

    “The settings the Narrate team turned away from their default on glossary words (begrip), sources (bron) and articles (artikel): whether an assistant may read it (ai_readable), whether it is findable …”

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

    1 input
    • kindstring“Only this kind.”
  • list_reader_conversations

    “The conversations with readers that the Narrate team shows under an article ("Gesprek in de marge"), with each reader's consent: the paragraph each answers and its messages, without any email address…”

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

    1 input, 1 required
    • articlestringrequired“The article's slug.”
  • “One of Narrate's partners as its landing page on the site shows it: name, logo, colour, tagline, description, a quote, and the partner's public programmes (accelerator, network or consultancy) with t…”

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

    2 inputs, 1 required
    • slugstringrequired“The partner's slug, as in its address on the site.”
    • programstring“A programme's slug, to have that programme in the answer even when it is not listed.”
  • list_ball_graph_positions

    “Where every ball of the ball graph on the public chart pages lies in the network view, worked out ahead of time: a map of ball id to [x, y] in whole units.”

    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 2026-11-14.

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 93
Tools with a description
100% of 37
Typical description length
385 characters

The tool set

Counted from the listing

Tools
37
Size of the list
about 16,816 tokens for an agent to load (characters ÷ 4)
Naming
37 of 37 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 37 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 2026-11-14 (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://narrate.works/mcp/public
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "public": {
      "url": "https://narrate.works/mcp/public"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "public": {
      "type": "http",
      "url": "https://narrate.works/mcp/public"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"public","type":"http","url":"https://narrate.works/mcp/public"}'
Claude Code
claude mcp add --transport http public https://narrate.works/mcp/public
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "public": {
      "type": "streamableHttp",
      "url": "https://narrate.works/mcp/public",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "public": {
      "httpUrl": "https://narrate.works/mcp/public"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.public]
url = "https://narrate.works/mcp/public"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "public": {
      "url": "https://narrate.works/mcp/public"
    }
  }
}
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://narrate.works/mcp/public --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 2026-11-12. 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 2026-11-12. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-12. Source: read 2026-11-12.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-12. Source: read 2026-11-12.

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 narrate.works/mcp/publicSession openedmatchesour test · 2026-11-14
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-14

Tool list changes

Our reads compared · no tool called

Hosted endpoint narrate.works/mcp/public

1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-11-12 to 2026-11-14; version 1.0.0).

Last change seen between our reads on 2026-11-12 (version 1.0.0) and 2026-11-14 (version 1.0.0). Changed without a new version: both reads list version 1.0.0.

Added (15):

get_client_evaluation_formget_partnerget_quote_to_signget_reference_settingslist_ball_graph_positionslist_framework_originslist_metricslist_reader_conversationspresentation_read_livepresentation_save_answerpresentation_sign_uprequest_beta_accessstart_quote_signingsubmit_client_evaluationterms_which_apply

Changed (3):

get_code_list: title, description, input schema, annotationslist_indicators: descriptionlist_shop_catalog: description

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 2026-11-14 is not known yet. No tool was called. How it is compared

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.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • 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 2026-11-12. 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 works.narrate/public

Answered from the data above

Who publishes works.narrate/public?

The registry ties the namespace works.narrate to the domain narrate.works; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does works.narrate/public need an API key or sign-in?

It opened a session without any credential on 2026-11-14. The registry entry declares no required credential; no declaration is not a guarantee.

Has works.narrate/public been security tested?

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

Found this page useful?

Anonymous · no sign-in

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

Compare with another server

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

Security testing

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

18 checks · features #1, #2

Open without sign-in

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

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

3 exercised12 not run (reason given)3 not applicable

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

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

Source: our own test, 2026-11-14, 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. 12,354 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 37 tools, 0 resources, 0 prompts.
  4. 43,818 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

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

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-12; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-11-12
MCP capability
resources, tools
our test · 2026-11-14
Transport
streamable HTTP
registry · 2026-11-12
Required credentials
none declared
registry · 2026-11-12 · 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 · 2026-11-12
Lifecycle status
registry · 2026-11-12
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 · 2026-11-12

“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. “works.narrate/public: MCP server record.” Data checked 2026-11-14. https://protocolprobe.com/mcp/servers/works.narrate/public

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: 1 of 2 record checks met

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

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