Provider REST API

10 actions

Connect Claude to Context7

Pull current, version-specific library documentation and code examples into an agent's context, and add your own repositories and sites to the index. Toolspoke puts 10 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key (optional)
Actions exposed: 10
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Context7
Open the marketplace in your workspace, add Context7 to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Nothing to connect. Context7 needs no credential.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Context7 shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Context7 asks for

Context7 needs no credential. There is nothing to go and fetch: the settings below are optional, and they are configuration rather than secrets.

API keyOptional: Optional. context7.com/dashboard → API Keys → Create API key. Without a key the documentation reads still work on the anonymous rate limit; get_usage, get_policies, get_library_metrics and every write need one.; ctx7sk-…

What Claude can do in Context7

10 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 6Reads
Writes: 4Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

search_libraries
Find the Context7 library ID for a product name, ranked against the question you are about to ask. Call this first unless you already have an exact ID such as /vercel/next.js; get_context needs one. Each result carries its versions, snippet count, trust score and indexing state.
get_context
Return the documentation snippets and code examples from one library that best answer a question. Pin a version by suffixing the ID, e.g. /vercel/[email protected]. Returns LLM-ready text unless type is json. A 202 means the library is still being indexed; try again later.
search_docs
Answer a question in one call - Context7 picks the libraries itself, optionally steered by up to four library hints and a version. Use it when you do not want the search_libraries then get_context round trip. Pasted error output is a valid query.
get_usage
Show this month's request count against the plan, extra spend, the teamspace spending limit and daily usage. Needs an API key. Does not count against the request quota.
get_policies
Read the teamspace's library policies - which source types are enabled and which public libraries its members may reach. The usual answer to "why does search not find a library I can see on context7.com". Needs an API key.
get_library_metrics
Request counts for a library this teamspace owns - totals by channel, daily history, MCP clients, top topics and countries. Needs a key from a member of the owning teamspace.

Writes

Creates or updates something on the other side.

refresh_library
Re-index a library from its source so new docs show up. Starts the refresh and returns at once. Needs an API key with rights over the library.
add_github_repo
Submit a GitHub repository for indexing. Returns the library ID it will live under. A public repository joins the public index; set private for one only your teamspace sees.
add_website
Submit a documentation website for crawling and indexing. Returns the library ID it will live under.
add_llmstxt
Submit an llms.txt, llms-full.txt or llms-small.txt file for indexing. Returns the library ID it will live under.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 10 actions above are the whole of it. A call to any other name is refused before it reaches Context7 rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Context7, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Context7 of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Context7: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Context7. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Context7's own rate limits. A call that Context7 refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Context7?

10 named actions: 6 that only read and 4 that write. They include search_libraries, get_context and search_docs. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Context7 connector need?

None at all. Context7 is reachable without one, so there is nothing of yours for Toolspoke to store. The connector does take api key as optional configuration.

Does the Context7 connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 10 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Context7 connector not do?

The 10 actions above are the whole of it. A call to any other name is refused before it reaches Context7 rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Context7, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Context7 of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Context7. An agent has to ask. Toolspoke does not retry, queue or back off around Context7's own rate limits. A call that Context7 refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Context7's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Context7?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More developer tools connectors

Browse all of them