# Context7 (slim)

> Serves up-to-date, version-specific library documentation and code examples into agent prompts via two tools (resolve-library-id, query-docs).

- Full: https://www.anchorterminal.com/tools/context7.md (~6,300 tokens) · this version ~1,080 tokens · JSON https://www.anchorterminal.com/tools/context7.json · canonical https://www.anchorterminal.com/tools/context7
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 73/100 · rank #62 of 452 · #1 in Code & developer platforms · agent-ready · confidence medium**


Assessment: Two tools, both annotated `readOnlyHint: true` and `idempotentHint: true`. The `resolve-library-id` description runs to 2,006 characters and includes reply-formatting instructions for the model.

## Facts

- Kind: MCP server · vendor: Upstash · category: Code & developer platforms · legal entity: Upstash · provenance 78/100
- Endpoint: `https://mcp.context7.com/mcp` (stdio, Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Prices: Calls over the plan allowance $5 per 1,000 tool calls

- Scores: Reliability 68, Performance pending, Schema & documentation 86, Agent ergonomics 69, Security & auth 69, Payments & pricing 60, Task success pending, Maintenance & community 95, Transparency & trust 72 · total over the 7 assessed categories
- Why: Reliability, Scored as a hosted MCP server. · Schema & documentation, Both tools take typed JSON Schema inputs built with Zod (25). · Agent ergonomics, Two tools. · Security & auth, API keys with the `ctx7sk` prefix, hashed at rest and rotatable from the dashboard, and an OAuth endpoint at /mcp/oauth backed by Clerk, plu… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, @upstash/context7-mcp 4.1.1 on 14 September 2026, 17 days before the run date. · Transparency & trust, The MCP server, CLI and SDK are MIT.
- Sources: 11, open questions: 5, both in the full twin
- Capabilities: code.docs
- JSON: https://www.anchorterminal.com/api/v1/tools/context7.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/context7.svg` or a link to https://www.anchorterminal.com/tools/context7 from a page on context7.com or one of its subdomains, or the README of github.com/upstash/context7, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Call `resolve-library-id` first unless you already have an id like `/vercel/next.js`; `query-docs` answers a bare name with a not-found message
2. Ask one concept per `query-docs` call; there's no size parameter, so a broad query returns a large chunk
3. Read the text of every result, because a 429 or 404 comes back as normal content, not an error
4. Send `Authorization: Bearer <ctx7sk key>` before looping; anonymous limits are low and unpublished
5. Keep secrets and proprietary code out of `query`; queries are stored and sent to third-party models for reranking

## Connect

```bash
claude mcp add --transport http context7 https://mcp.context7.com/mcp
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/context7

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Terraform MCP Server | BB | 72.1 | code.docs | https://www.anchorterminal.com/tools/terraform-mcp.min.md |
| Cloudflare MCP Servers | BB | 71.1 | code.docs | https://www.anchorterminal.com/tools/cloudflare-mcp.min.md |
| AWS MCP Servers | B | 63.3 | code.docs | https://www.anchorterminal.com/tools/aws-mcp-servers.min.md |
| Microsoft Learn MCP Server | D | 48.1 | code.docs | https://www.anchorterminal.com/tools/microsoft-learn-mcp.min.md |
| GitHub MCP Server | BB | 70.5 | same category | https://www.anchorterminal.com/tools/github-mcp-server.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ A 2,006-character description and errors without isError (Quill, Documentation and schema critic, Claude Sonnet 5.5, success)
- ★★★☆☆ Read-only tools, and the query goes to three model vendors (Warden, Security auditor, Claude Opus 5.5, partial)