ContextSAFE
Self-hosted MCP server for your documentation
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Self-hosted MCP server for your documentation. Index your documentation from across the sources and serve it via the Model Context Protocol (MCP) and REST API.
Quick Start
# Scaffold a new project npx contextmcp init my-docs-mcp # Follow the prompts, then: cd my-docs-mcp npm install # Configure your API keys cp .env.example .env # Edit .env with your PINECONE_API_KEY and an embedding provider key # (OPENAI_API_KEY for provider: openai, or GEMINI_API_KEY for provider: gemini) # Configure your documentation sources # Edit config.yaml # Index your documentation npm run reindex # Edit the cloudflare-worker # Deploy the MCP server cd cloudflare-worker npm install npm run deploy
What is ContextMCP?
ContextMCP creates a searchable knowledge base from your documentation that AI assistants can query via the Model Context Protocol (MCP).
Supported Content Types
How It Works
- Parse - Extract content from your docs, APIs, and READMEs
- Chunk - Split into semantic chunks optimized for search
- Embed - Generate embeddings using OpenAI or Gemini
- Store - Upload to Pinecone vector database
- Search - Query via MCP from
36eedcf4586fOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add contextmcp-website --env COHERE_API_KEY=${COHERE_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env PINECONE_API_KEY=${PINECONE_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"contextmcp-website": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"COHERE_API_KEY": "${COHERE_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"PINECONE_API_KEY": "${PINECONE_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
search_docs | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (7 observation(s))
- Network
- declared (8 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
# ContextMCP Configuration for Dodo Payments
const srcDir = path.resolve(__dirname, '../../template');
path.resolve(__dirname, '../../template'),
} from '../../src/search-core';
const CANONICAL = resolve(here, '../../src/search-core.ts');
import { renderVendored, readCanonical, readVendored, PATHS } from '../../scripts/sync-shared.mjs';base = `http://127.0.0.1:${port}`;base = `http://127.0.0.1:${port}`;@google/genai, @pinecone-database/pinecone, agents, ai, openai, zod, @cloudflare/workers-types, typescript
prettier, tsx, typescript, wrangler
chalk, commander, fs-extra, ora, prompts, @types/fs-extra, @types/node, @types/prompts
@google/genai, @pinecone-database/pinecone, agents, ai, openai, zod, @cloudflare/workers-types, typescript
@pinecone-database/pinecone, dotenv, gray-matter, node-html-parser, openai, tiktoken, turndown, yaml
Gates applied: no_behavioural_pass.
36eedcf4586ffull audit observations/trust-audit/mcp-server/dodopayments__context-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 36eedcf4586f | SAFE | B | 89 | first audit |
Questions
What is the Context MCP server?
Self-hosted MCP server for your documentation
What tools does Context expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Context safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Context need?
It reads COHERE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, PINECONE_API_KEY and VOYAGE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Context run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as contextmcp-website at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (36eedcf4586f), read on 2026-10-07. The repository is watched and re-audited when it changes.