Local semantic code search with Git history. Works offline, no API key needed.
Code MCP server exists for a simple reason — assistants are far more useful when they can act on Code directly instead of describing what you should do. Local semantic code search with Git history. Works offline, no API key needed.
A deterministic, high-precision code intelligence layer exposed as a Model Context Protocol (MCP) server.
Once Code is connected, these are the calls the assistant has available:
Prerequisites — The Prerequisites tool exposed by this serverDevelopment — The Development tool exposed by this serverindex_codebase — Indexes or re-indexes source files and documentation in the given directory. Run this before using search_code or search_docs to ensure the databasesearch_code — Perform semantic search and find structural code definitions, locate where functions/classes are defined, or map out dependency references (callsearch_docs — Understand the codebase conceptually — how things work, architectural patterns, SOPs. Searches markdown documentation, READMEs, and docstringssearch_history — Debug regressions and understand developer intent through Git historycode-memory on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need one environment variable: EMBEDDING_MODEL. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
uv package manager (recommended) or pip Install uv if you don't have it:Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Code's toolset — Prerequisites, Development, index_codebase and 3 more — is a fair guide to whether it matches your workflow. It is maintained by kapillamba4; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Prerequisites | The Prerequisites tool exposed by this server. |
| Development | The Development tool exposed by this server. |
| index_codebase | Indexes or re-indexes source files and documentation in the given directory. Run this before using search_code or search_docs to ensure the database is up to date. Uses tree-sitter for language-agnostic structural extrac |
| search_code | Perform semantic search and find structural code definitions, locate where functions/classes are defined, or map out dependency references (call graphs). Uses hybrid retrieval (BM25 + vector embeddings) to find exact mat |
| search_docs | Understand the codebase conceptually — how things work, architectural patterns, SOPs. Searches markdown documentation, READMEs, and docstrings extracted from code. |
| search_history | Debug regressions and understand developer intent through Git history. |
For Windows:
```json
{
"mcpServers": {
"code-memory": {
"command": "C:\\path\\to\\code-memory-windows-x86_64.exe"
}
}
}Configuration as documented by the project. Restart the client after saving.
uv package manager (recommended) or pip Install uv if you don't have it:| Variable | Description | Required |
|---|---|---|
| EMBEDDING_MODEL | Configuration value read at startup. | Optional |
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.