
Farm.js MCP server
Which servers in the official MCP registry are Farm.js's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namedev.farmjs/docsverified in the MCP registry
The registry name sits under farmjs.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools10
- Server calls itselfFarm.js
- Server version0.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 133 ms.
- Its tools do none of the product's use cases we checked: define typed API routes consumed by a generated client; connect billing and API-key services through typed integrations; build and deploy an application as one production bundle.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 10 of 10 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it0 of 3 use cases
- Use576 GitHub stars
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer590 ms
- Space in an agent's context≈ 1,528 tokensthe definitions of all its tools (10), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results10 of 10 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 10 of 10
What an agent can do with it
- cannot · define typed API routes consumed by a generated client
- cannot · connect billing and API-key services through typed integrations
- cannot · build and deploy an application as one production bundle
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_code_examplesReturn fenced code examples from the docs with parsed metadata such as title, framework, packageManager, and runnable.
get_config_schemaReturn structured docs.config.ts option metadata, optionally filtered by option path or query.
get_contextBuild deterministic, section-level documentation context for a query within a conservative UTF-8 byte ceiling derived from the requested token budget, with source URLs and accounting metadata.
get_navigationReturn the documentation navigation tree for the current docs site.
hydrate_content_changesFetch only added and changed agent-facing sections after list_content_changes. Returns deletion tombstones and digest-bound continuation cursors under a conservative token budget.
list_content_changesSynchronize body-free document metadata. Save indexGeneration and pass it as since on the next poll. A reset response means the named snapshot is no longer available.
list_docsList documentation pages grouped by section, optionally narrowed to one section.
list_page_sectionsDiscover a page's canonical headings, anchors, hierarchy, line ranges, size estimates, and budget-aware fetch URLs without returning the page body.
list_pagesList the known documentation pages with titles, slugs, and URLs.
list_search_facetsList valid framework, version, package, and tag filters with matching page counts before calling search_docs. Use facet, limit, and cursor to continue a large facet without document bodies.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"docs": {
"type": "http",
"url": "https://mcp.farmjs.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http farmjs https://mcp.farmjs.dev/mcpclaude.ai, ChatGPT and other clients: add https://mcp.farmjs.dev/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.