Code indexing for better AI code generation
Kodit MCP server exists for a simple reason — assistants are far more useful when they can act on Kodit directly instead of describing what you should do. Code indexing for better AI code generation.
A code and document intelligence server that indexes Git repositories and provides search through MCP and REST APIs.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Kodit is connected, these are the calls the assistant has available:
kodit_repositories — List all indexed repositorieskodit_semantic_search — Semantic similarity search across codekodit_keyword_search — BM25 keyword searchkodit_visual_search — Search document page imageskodit_grep — Regex pattern matchingkodit_ls — List files by glob patternkodit_read_resource — Read file content by URIkodit_architecture_docs — Architecture documentation for a repokodit_api_docs — Public API documentationkodit_database_schema — Database schema documentationkodit_cookbook — Usage examples and patternskodit_commit_description — Commit descriptionYou will need 8 environment variables: ENRICHMENT_ENDPOINT_BASE_URL, EMBEDDING_ENDPOINT_API_KEY, EMBEDDING_ENDPOINT_BASE_URL, EMBEDDING_ENDPOINT_SOCKET_PATH, BASE_URL, VISION_EMBEDDING_ENDPOINT_BASE_URL, VISION_EMBEDDING_ENDPOINT_API_KEY, VISION_EMBEDDING_ENDPOINT_SOCKET_PATH. 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.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Kodit's toolset — kodit_repositories, kodit_semantic_search, kodit_keyword_search and 11 more — is a fair guide to whether it matches your workflow.
This entry was verified against Kodit's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| kodit_repositories | List all indexed repositories |
| kodit_semantic_search | Semantic similarity search across code |
| kodit_keyword_search | BM25 keyword search |
| kodit_visual_search | Search document page images |
| kodit_grep | Regex pattern matching |
| kodit_ls | List files by glob pattern |
| kodit_read_resource | Read file content by URI |
| kodit_architecture_docs | Architecture documentation for a repo |
| kodit_api_docs | Public API documentation |
| kodit_database_schema | Database schema documentation |
| kodit_cookbook | Usage examples and patterns |
| kodit_commit_description | Commit description |
| kodit_wiki | Wiki table of contents |
| kodit_wiki_page | Read a specific wiki page |
{
"mcpServers": {
"kodit": {
"command": "docker",
"args": ["run", "-i", "--rm", "registry.helix.ml/helix/kodit"],
"env": {
"ENRICHMENT_ENDPOINT_BASE_URL": "your-value",
"EMBEDDING_ENDPOINT_API_KEY": "your-value",
"EMBEDDING_ENDPOINT_BASE_URL": "your-value",
"EMBEDDING_ENDPOINT_SOCKET_PATH": "your-value",
"BASE_URL": "your-value",
"VISION_EMBEDDING_ENDPOINT_BASE_URL": "your-value",
"VISION_EMBEDDING_ENDPOINT_API_KEY": "your-value",
"VISION_EMBEDDING_ENDPOINT_SOCKET_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| ENRICHMENT_ENDPOINT_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| EMBEDDING_ENDPOINT_API_KEY | Credential the server authenticates with. | Yes |
| EMBEDDING_ENDPOINT_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| EMBEDDING_ENDPOINT_SOCKET_PATH | Filesystem location the server is allowed to use. | Optional |
| BASE_URL | Endpoint or connection string the server talks to. | Yes |
| VISION_EMBEDDING_ENDPOINT_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| VISION_EMBEDDING_ENDPOINT_API_KEY | Credential the server authenticates with. | Yes |
| VISION_EMBEDDING_ENDPOINT_SOCKET_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.