Skip to content

Release v0.9.12

Choose a tag to compare

@github-actions github-actions released this 29 Jan 00:45
· 4 commits to main since this release

Weave MCP Server v0.9.12

Changes since v0.9.10

  • chore: Update weave-cli dependency to v0.9.12
  • test: Improve integration test log messages for clarity
  • docs: Move upgrade planning docs to docs/planning

Downloads

  • Linux AMD64: weave-mcp-linux-amd64
  • Linux ARM64: weave-mcp-linux-arm64
  • macOS AMD64: weave-mcp-darwin-amd64
  • macOS ARM64: weave-mcp-darwin-arm64
  • Windows AMD64: weave-mcp-windows-amd64.exe

Note: Chroma vector database is excluded from release binaries due to CGO requirements.
Release binaries support 10 vector databases: Weaviate, Supabase, MongoDB, Milvus,
Qdrant, Neo4j, Pinecone, OpenSearch, Elasticsearch, and Mock.

For Chroma support, build from source on macOS using ./build.sh.

Installation

Download the appropriate binary for your platform and make it
executable:

# Linux/macOS
chmod +x weave-mcp-linux-amd64
mv weave-mcp-linux-amd64 /usr/local/bin/weave-mcp
weave-mcp --version

# Windows
weave-mcp-windows-amd64.exe --version

Verification

Verify the integrity of the downloaded binary:

sha256sum -c checksums.txt

Usage

Start the MCP server:

# Using the binary directly
./weave-mcp --help

# Or using the start script (if you have the full repository)
./start.sh

Configuration

The server requires a config.yaml file and .env file. See the
README for detailed configuration instructions.

MCP Tools

The server exposes the following MCP tools:

  • list_collections - List all collections
  • create_collection - Create a new collection
  • delete_collection - Delete a collection
  • list_documents - List documents in a collection
  • create_document - Create a new document
  • batch_create_documents - Create multiple documents at once
  • get_document - Retrieve a specific document
  • update_document - Update a document's content or metadata
  • delete_document - Delete a document
  • count_documents - Count documents in a collection
  • query_documents - Perform semantic search

See the README for detailed API documentation and examples.