tc39-mcp

Independent MCP server for the TC39 specs (ECMA-262 + ECMA-402): clauses, search, diffs, history.

Should I use this

Quality & Safety

B
Description quality
96%
Schema completeness
72%
Naming quality
51%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (18)

  • LOWTool 'spec.symbol_resolve' description lacks action verbin spec.symbol_resolve
  • LOWTool 'spec.about' doesn't follow camelCase/snake_casein spec.about
  • LOWTool 'clause.get' doesn't follow camelCase/snake_casein clause.get
  • LOWTool 'clause.list' doesn't follow camelCase/snake_casein clause.list
  • LOWTool 'spec.search' doesn't follow camelCase/snake_casein spec.search
  • LOWTool 'proposal.list' doesn't follow camelCase/snake_casein proposal.list
  • LOWTool 'proposal.get' doesn't follow camelCase/snake_casein proposal.get
  • LOWTool 'spec.grammar' doesn't follow camelCase/snake_casein spec.grammar
  • LOWTool 'spec.tables' doesn't follow camelCase/snake_casein spec.tables
  • LOWTool 'spec.sdo_index' doesn't follow camelCase/snake_casein spec.sdo_index

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~2,038Tokens (tool definitions)
~536 BTypical response size
Moderate attention impact (1.59% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "tc39-mcp": {
      "command": "npx",
      "args": [
        "tc39-mcp"
      ]
    }
  }
}

Runnable packages

npmtc39-mcp0.6.3stdio

Remote endpoints

https://tc39-mcp.chicoxyzzy.workers.dev/mcpstreamable-http
https://mcp.xyzzylabs.ai/tc39/mcpstreamable-http

What it can do

Tool inventory

Tools (17)

๐ŸŸข Read-only๐ŸŸก Write๐Ÿ”ด Deleteโšช Unknown
โšชspec.about

Self-description of this MCP server: package name + version, per-snapshot pin metadata (sha, fetched_at, biblio_commit, clause_count) for every supported (spec, edition), plus test262 + proposals index headers when present.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
๐ŸŸขclause.get(id, spec, edition, at)

Fetch a parsed TC39 clause as structured JSON. `spec` selects '262' (default) or '402'. `edition` defaults to 'latest'. `at: '<sha>'` pins to a historical main snapshot (only valid for edition='main'); omit to query the live snapshot.

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "at": {
      "type": "string",
      "description": "Optional historical SHA pin (hex, 4-40 chars). Only valid when edition='main'; released editions have no per-SHA history to address."
    }
  },
  "required": [
    "id"
  ]
}
๐ŸŸขclause.list(spec, edition, at, kind, section, ...)

List parsed spec clauses with optional filters (kind, section prefix, has_algorithm). `spec` selects '262' or '402'. `at: '<sha>'` queries a historical main snapshot.

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "at": {
      "type": "string"
    },
    "kind": {
      "type": "string"
    },
    "section": {
      "type": "string"
    },
    "has_algorithm": {
      "type": "boolean"
    },
    "limit": {
      "type": "number"
    }
  }
}
๐ŸŸขspec.search(query, spec, edition, at, limit, ...)

Search the parsed spec by clause id / aoid / title (+ step text with `search_steps`). Aoid-exact ranks first. `at: '<sha>'` searches a historical main snapshot.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "at": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "search_steps": {
      "type": "boolean"
    }
  },
  "required": [
    "query"
  ]
}
๐ŸŸขproposal.list(spec, stage, champion, contains, limit)

List TC39 proposals from the static index (tc39/proposals). Filter by spec ('262'|'402'), stage ('0'|'1'|'2'|'2.7'|'3'|'finished'|'inactive'|'active'), champion (substring), or contains (name/slug substring).

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "stage": {
      "type": "string"
    },
    "champion": {
      "type": "string"
    },
    "contains": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}
๐ŸŸขproposal.get(name)

Fetch one TC39 proposal by slug (exact) or name (case-insensitive).

Input Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    }
  },
  "required": [
    "name"
  ]
}
๐ŸŸขspec.grammar(nonterminal, contains, include_sdo, spec, edition, ...)

Query grammar productions captured from the spec's `<emu-grammar>` blocks. `{ nonterminal }` returns every production for that non-terminal (exact match); `{ contains }` filters by RHS / name substring; neither lists all non-terminals + their production counts. `include_sdo` folds in SDO-attached productions (off by default).

Input Schema

{
  "type": "object",
  "properties": {
    "nonterminal": {
      "type": "string"
    },
    "contains": {
      "type": "string"
    },
    "include_sdo": {
      "type": "boolean"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}
๐ŸŸขspec.tables(id, filter, spec, edition, limit)

List or fetch parsed `<emu-table>` content. `{ id }` returns exactly that table (full columns + rows); otherwise list table summaries, optionally narrowed by a `filter` substring over the caption or id.

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "filter": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}
โšชspec.sdo_index(spec, edition, by, filter, limit)

Index Syntax-Directed Operations by the grammar production they're defined on. `by: 'production'` (default) groups SDOs under each production; `by: 'sdo'` groups productions under each SDO title. `filter` narrows to keys containing a substring (case-insensitive).

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "by": {
      "type": "string",
      "enum": [
        "production",
        "sdo"
      ]
    },
    "filter": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}
โšชclause.outline(spec, edition, depth, under)

Return the section tree (table of contents) for a parsed (spec, edition). `depth` caps how deep the tree descends (1 = top-level only); `under` limits the tree to descendants of one clause id.

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "depth": {
      "type": "number"
    },
    "under": {
      "type": "string"
    }
  }
}
๐ŸŸขspec.global_search(query, search_steps, limit)

Run spec.search across both ECMA-262 and ECMA-402 in one call and interleave hits by score. Each hit is tagged with the spec it came from. Use it when you don't know which spec defines a symbol. `search_steps` also matches algorithm step text.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "search_steps": {
      "type": "boolean"
    },
    "limit": {
      "type": "number"
    }
  },
  "required": [
    "query"
  ]
}
๐ŸŸขspec.snapshots(spec, edition)

List the live (spec, edition, sha, fetched_at) snapshots the hosted Worker is serving from R2. Filter by `spec` ('262'|'402') or `edition` (e.g. 'main', 'es2026'). Historical SHA-pinned copies are reachable via `at:` on clause.get / spec.search but aren't enumerated here.

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    }
  }
}
โšชspec.symbol_resolve(notation, spec, edition, limit)

Resolve spec notation like `[[Prototype]]` (internal slot), `%Object.prototype%` (well-known intrinsic), or `~number~` (sigil enum): return clauses that mention or define it, ranked by occurrence with a bump for definition-y sections.

Input Schema

{
  "type": "object",
  "properties": {
    "notation": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  },
  "required": [
    "notation"
  ]
}
โšชspec.well_known_intrinsics(spec, edition, filter, limit)

Enumerate the well-known intrinsics in a spec with their probable defining clauses. Driven from the canonical ยง6.1.7.4 WKI table when present (ECMA-262), else a `%X%` prose scan (e.g. ECMA-402). `filter` narrows by bare-name substring.

Input Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "filter": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}
โšชspec.diff(id, spec, from, to)

Clause-level diff of one clause across two editions of a spec. Reports identical / modified / added / removed plus a field-level breakdown (title, signature, step count, reworded step indices, notes, crossrefs). `from` defaults to the latest stable release, `to` to main.

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "from": {
      "type": "string"
    },
    "to": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}
๐ŸŸกspec.crossrefs(id, spec, edition, direction, include_cross_spec, ...)

For a clause id, return its outgoing references (clauses it cites) and/or incoming references (clauses that cite it โ€” the back-reference index the parse alone doesn't expose). The reverse index is AOID-densified from step text. `direction`: 'in' | 'out' | 'both' (default). Outgoing also carries an `external` category: the clause's citations to external specs (Unicode, IETF, WHATWG) as resolvable URLs. Set `include_cross_spec: true` to also resolve outgoing references from ECMA-262 โ†’ ECMA-402 (or vice versa).

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "spec": {
      "type": "string",
      "enum": [
        "262",
        "402"
      ]
    },
    "edition": {
      "type": "string"
    },
    "direction": {
      "type": "string",
      "enum": [
        "in",
        "out",
        "both"
      ]
    },
    "include_cross_spec": {
      "type": "boolean"
    },
    "limit": {
      "type": "number"
    }
  },
  "required": [
    "id"
  ]
}
๐ŸŸขtest262.search(query, esid, limit)

Search the tc39/test262 conformance suite from its indexed front-matter. `query` AND-matches whitespace tokens (case-insensitive) across each test's description + path; `esid` prefix-matches the front-matter esid. Returns ranked hits (path, GitHub url at the indexed SHA, esid, description, features, flags), capped at `limit` (default 20). Supply at least one of `query` / `esid`.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "esid": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    }
  }
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded17 tools
verifiedversion not recorded17 tools
verifiedversion not recorded17 tools
verifiedversion not recorded17 tools
verifiedversion not recorded17 tools
verifiedversion not recorded17 tools