Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Narrate is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
Narrate's public knowledge on impact management, for your AI assistant.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http narrate-mcp https://narrate.works/mcp/public
# 2 — ask your agent for something these tools do
# search_glossary, get_glossary_term, search_pages and 9 more
Narrate costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NAAll 1 server
narrate1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http narrate-mcp https://narrate.works/mcp/publicReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the words Narrate uses for impact management (begrippen), in Dutch or English. Matches the word, its synonyms and other spellings, its translation, the words it replaces and its definition. Use it before writing about impact, so you use Narrate's words and avoid the ones it replaces.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A word or phrase, e.g. 'stakeholder' or 'outtake'. Empty lists every word. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
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 confuse it with, and its source.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The stable id, e.g. 'rechthebbenden'. |
Search the public pages of narrate.works (articles, guides, materials, the glossary) by title, description and full text. Returns paths to read with read_page, with a short fragment where the words occur in the text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Words to look for in the title, the description or the text. |
| lang | string | no | 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). Use a path from search_pages, e.g. '/naslag/begrippen' or '/reference/glossary'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | The site path, starting with '/'. |
Search the sources Narrate cites (reports, laws, standards, books, our own counts) by title, publisher or id. Returns ids to read with get_source. Cite a source by its own title, publisher and URL, not as Narrate's claim.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Words to look for in the title or publisher, e.g. 'CSRD' or 'OECD'. Empty lists the most recently consulted. |
| lang | string | no | 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, and whether something overtook it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The stable id, e.g. 'csrd'. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
The keywords Narrate tags its work with, by group: perspectives, phases, challenges, sectors, organisational forms, frameworks, technology and product forms. Each keyword links to the page where it lives, to read with read_page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A word to look for, e.g. 'energie' or 'theory'. Empty lists every keyword. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
Narrate's published articles, newest first, as on narrate.works/materialen/artikelen (English /resources/articles). Choose a form to get one category: opinion gives the opinion pieces (/materialen/artikelen/opinie), guide the guides, longread the long reads, story the stories from practice, note the notes, ourWork the pieces on how we work. Returns each with its title, description, form, date, URL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| form | string | no | Only the articles of this form (category). Leave it out for every article. |
| query | string | no | Words to look for in the title or description. Empty lists them all. |
| limit | integer | no | How many articles, newest first. |
| lang | string | no | 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. The same answer as narrate.works/api/status and the status page. When Supabase itself is down this tool may not answer either; narrate.works/api/status then still does.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
The specials: Narrate's long, illustrated articles, with figures you can explore. Returns each with its title, description and path; read one in full with read_page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words to look for in the title or description. Empty lists every special. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
The societal challenges and sectors where Narrate did work for one audience group, taken only from the cases and clients its own page shows. A group without such proof gets an empty list. Name the group by its key ('municipalities') or the slug of its page ('gemeenten').
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audience | string | yes | The group: its key or the last part of its address, e.g. 'gemeenten' or 'municipalities'. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
Hand Narrate's team a suggestion without an account: a correction to a page or a glossary word, a missing source, an idea. Say what it is about (subject) and what should change and why (body). Never put personal data in it, such as a name, an email address or a phone number: the suggestion is anonymous and Narrate cannot answer it. The team reads every suggestion; there is no reply through this se
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | string | yes | What it is about, in a few words: a page path, a glossary word, 'the source register'. |
| body | string | yes | What should change, and why. |
| lang | string | no | Language of the text and the answer: nl (Dutch) or en (British English). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Narrate or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 11 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest5a5fe8db7a30fdc2d7210b1f0b745c3ea5edd5025eff8713ee371b18dabb4910
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_glossary | no tags | |
| get_glossary_term | no tags | |
| search_pages | no tags | |
| read_page | no tags | |
| search_sources | no tags | |
| get_source | no tags | |
| search_keywords | no tags | |
| list_articles | no tags | |
| get_status | no tags | |
| list_specials | no tags | |
| get_audience_fields | no tags | |
| suggest_change | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest5a5fe8db7a30fdc2
Scanned2026-11-11
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Narrate can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.