Skip to main content
Glama
QCObjects

product-specs-mcp

by QCObjects
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

product-specs-mcp

MCP server over the QCObjects product-specs docs — lets AI agents learn framework usage for building apps (specs 01–16 + examples). Runs on Cloudflare Workers via Streamable HTTP (stateless).

Tools

Tool

What it does

list_specs

Lists all 16 spec docs with site paths

search_docs

Full-text search over the published site (title-weighted ranking)

get_page

Fetches a docs page as plain text (~12k chars)

get_spec

Fetches one numbered spec (01–16) as plain text

docs_status

Returns the docs base URL (provenance)

Endpoints: GET / (health) · POST /mcp (MCP Streamable HTTP).

Related MCP server: openai-agents-sdk-mcp

How it reads the docs

No vendored content — the Worker fetches the live Pages site at runtime: search/search_index.json for search (cached per isolate, INDEX_TTL_SECONDS), page HTML stripped to text for reads. Override the source with the DOCS_BASE_URL var (e.g. a preview deploy).

Local dev

npm ci
npm run check   # tsc + vitest
npm run dev     # wrangler dev (http://127.0.0.1:8787)

Deploy (Cloudflare Workers)

CI deploys main automatically. Required GitHub Actions secrets (repo Settings → Secrets and variables → Actions):

Secret

Value

CLOUDFLARE_API_TOKEN

API token with Workers Scripts: Edit on the account (create at dash.cloudflare.com → My Profile → API Tokens)

CLOUDFLARE_ACCOUNT_ID

Account ID (Workers & Pages → Overview, right sidebar)

Manual deploy: wrangler login && npm run deploy.

Git workflow

Topic branches from development (feature/*), PR into development, release development → main. Never rebase. SSH only.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Documentation Fetcher & RAG

    mikkelkrogsholm
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to fetch, index, and perform semantic RAG-based searches on API documentation from various sources. It provides tools for hybrid search and collection management, allowing users to access up-to-date documentation from projects like Gemini and FastMCP.
    -

  • openai-agents-sdk-mcp

    gavinz0228
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides MCP tools to list and search OpenAI Agents SDK documentation, enabling LLMs to retrieve documentation topics and content via natural language queries.
    45 PyPI
    MIT

  • Hermes MCP Server

    darrenzwchan
    A
    license
    A
    quality
    D
    maintenance
    Transforms internal Hermes documents (PRDs, RFCs, specs) into agent tools for relevance search, metadata, and full content retrieval, plus a skill to cross-check specs against code.
    8
    519 npm
    MIT

  • natural-docs-mcp

    jsharma103
    A
    license
    A
    quality
    D
    maintenance
    Provides read-only tools to search, read, and look up Natural API documentation from an AI agent, enabling documentation lookup without credentials.
    4
    MIT