MCP server for ChromaDB with fast batch file processing - ingest photos, CAD files, documents & code
Chromadblocal MCP server exists for a simple reason — assistants are far more useful when they can act on Chromadblocal directly instead of describing what you should do. MCP server for ChromaDB with fast batch file processing - ingest photos, CAD files, documents & code.
A Model Context Protocol (MCP) server that gives AI assistants persistent memory through ChromaDB vector storage. Now with EXIF extraction, Watch Folders, and Duplicate Detection - the ultimate tool for creators!
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Once Chromadblocal is connected, these are the calls the assistant has available:
Core — The Core tool exposed by this serverPrerequisites — The Prerequisites tool exposed by this serverInstallation — 1. Clone the repository bash git clone https://github.com//vespo92/chromadblocal-mcp-server.git cd chromadb-mcp-serversearch_context — Search for relevant information across collections Parameters: - query: Search query - collection: (optional) Specific collection to search - limitstore_context — Store new information with metadata Parameters: - content: The content to store - metadata: Tags, categories, descriptions - collection: Targetlist_collections — The list_collections tool exposed by this serverfind_similar_patterns — The find_similar_patterns tool exposed by this serverscan_directory — Preview files in a directory before ingesting Parameters: - path: Directory to scan - categories: Filter by type (images, cad, documents, data, code)batch_ingest — Bulk ingest files into ChromaDB with full metadata Parameters: - path: Source directory - collection: Target collection name - categories: File typesquick_load — 🚀 FAST: Rapidly load files for temporary processing Parameters: - path: Directory to load - name: Collection name (auto-generated if omitted) -unload_collection — Delete a collection (cleanup after quick_load) Parameters: - collection: Name of collection to deleteexport_collection — Export collection to JSON file Parameters: - collection: Collection to export - output_path: File path for JSON outputYou will need one environment variable: CHROMADB_URL. 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.
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. Chromadblocal's toolset — Core, Prerequisites, Installation and 11 more — is a fair guide to whether it matches your workflow. It is maintained by vespo92; 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 |
|---|---|
| Core | The Core tool exposed by this server. |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Installation | 1. **Clone the repository** bash git clone https://github.com//vespo92/chromadblocal-mcp-server.git cd chromadb-mcp-server |
| search_context | Search for relevant information across collections Parameters: - query: Search query - collection: (optional) Specific collection to search - limit: (optional) Number of results |
| store_context | Store new information with metadata Parameters: - content: The content to store - metadata: Tags, categories, descriptions - collection: Target collection |
| list_collections | The list_collections tool exposed by this server. |
| find_similar_patterns | The find_similar_patterns tool exposed by this server. |
| scan_directory | Preview files in a directory before ingesting Parameters: - path: Directory to scan - categories: Filter by type (images, cad, documents, data, code) - extensions: Filter by extension (.jpg, .stl, etc.) - recursive: Incl |
| batch_ingest | Bulk ingest files into ChromaDB with full metadata Parameters: - path: Source directory - collection: Target collection name - categories: File types to include - max_files: Limit number of files |
| quick_load | 🚀 FAST: Rapidly load files for temporary processing Parameters: - path: Directory to load - name: Collection name (auto-generated if omitted) - categories: File types to include |
| unload_collection | Delete a collection (cleanup after quick_load) Parameters: - collection: Name of collection to delete |
| export_collection | Export collection to JSON file Parameters: - collection: Collection to export - output_path: File path for JSON output |
| import_collection | Import collection from JSON file Parameters: - input_path: JSON file to import - collection: Override collection name - overwrite: Delete existing first (default: false) |
| get_collection_info | Get detailed stats about a collection Parameters: - collection: Collection name |
{
"mcpServers": {
"chromadb-context": {
"command": "bun",
"args": ["run", "/path/to/chromadb-mcp-server/index.js"],
"env": {
"CHROMADB_URL": "http://localhost:8001"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| CHROMADB_URL | Endpoint or connection string the server talks to. | 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.