A local MCP server for searching official PipeCD docs.
PipeCD Docs MCP server exists for a simple reason — assistants are far more useful when they can act on PipeCD Docs directly instead of describing what you should do. A local MCP server for searching official PipeCD docs.
This server clones the official PipeCD docs from GitHub and provides simple full-text search and document retrieval APIs via the MCP protocol. Documentation is cloned into a temporary directory, and Markdown files are indexed by extracting their titles and content.
Once PipeCD Docs is connected, these are the calls the assistant has available:
Prerequisites — 1. Create a PAT with read:packages scope. [Details](https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-npm-rCursor — The Cursor tool exposed by this serversearch_docs — The search_docs tool exposed by this serverread_docs — The read_docs tool exposed by this serverImprovements — The Improvements tool exposed by this serverYou will need one environment variable: YOUR_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
read:packages scope. Details 2. Add the following config to your .npmrc file.Installation goes through your MCP client rather than a global install: point it at Add on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. PipeCD Docs's toolset — Prerequisites, Cursor, search_docs and 2 more — is a fair guide to whether it matches your workflow. It is maintained by pipe-cd; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Prerequisites | 1. Create a PAT with read:packages scope. [Details](https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-npm-registry) |
| Cursor | The Cursor tool exposed by this server. |
| search_docs | The search_docs tool exposed by this server. |
| read_docs | The read_docs tool exposed by this server. |
| Improvements | The Improvements tool exposed by this server. |
{
"mcpServers": {
"docs-mcp-server-pipe-cd": {
"command": "npx",
"args": ["-y", "Add"],
"env": {
"YOUR_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
read:packages scope. Details 2. Add the following config to your .npmrc file.| Variable | Description | Required |
|---|---|---|
| YOUR_TOKEN | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.