Waggle-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WAGGLE_MODEL | No | Sentence-transformers model for local embeddings | all-MiniLM-L6-v2 |
| WAGGLE_BACKEND | No | Backend database type: 'sqlite' or 'neo4j' | sqlite |
| WAGGLE_DB_PATH | No | Path to SQLite database file (used with WAGGLE_BACKEND=sqlite) | memory.db |
| WAGGLE_HTTP_HOST | No | Bind host for HTTP service (used with WAGGLE_TRANSPORT=http) | 0.0.0.0 |
| WAGGLE_HTTP_PORT | No | Bind port for HTTP service (used with WAGGLE_TRANSPORT=http) | 8080 |
| WAGGLE_LOG_LEVEL | No | Log level | INFO |
| WAGGLE_NEO4J_URI | No | Neo4j Bolt URI, e.g. 'bolt://localhost:7687' (required with WAGGLE_BACKEND=neo4j) | |
| WAGGLE_TRANSPORT | No | Transport mode: 'stdio' or 'http' | stdio |
| WAGGLE_EXPORT_DIR | No | Optional export directory | |
| WAGGLE_OLLAMA_URL | No | Base URL for local Ollama (used with WAGGLE_EXTRACT_BACKEND=llm) | http://localhost:11434 |
| WAGGLE_EXTRACT_MODEL | No | Ollama model name for extraction (used with WAGGLE_EXTRACT_BACKEND=llm) | mistral |
| WAGGLE_NEO4J_DATABASE | No | Neo4j database name (used with WAGGLE_BACKEND=neo4j) | |
| WAGGLE_NEO4J_PASSWORD | No | Neo4j password (required with WAGGLE_BACKEND=neo4j) | |
| WAGGLE_NEO4J_USERNAME | No | Neo4j username (required with WAGGLE_BACKEND=neo4j) | |
| WAGGLE_RATE_LIMIT_RPM | No | Global rate limit (requests per minute) | 120 |
| WAGGLE_EXTRACT_BACKEND | No | Extraction backend: 'auto', 'llm', or 'regex' | auto |
| WAGGLE_DEFAULT_TENANT_ID | No | Default tenant ID | local-default |
| WAGGLE_MAX_PAYLOAD_BYTES | No | Max request size in bytes | 1048576 |
| WAGGLE_WRITE_RATE_LIMIT_RPM | No | Write-tool rate limit (requests per minute) | 60 |
| WAGGLE_EXTRACT_MIN_CONFIDENCE | No | Minimum confidence threshold for extraction (float 0-1) | 0.5 |
| WAGGLE_OLLAMA_TIMEOUT_SECONDS | No | Timeout in seconds for Ollama requests | 15 |
| WAGGLE_MAX_CONCURRENT_REQUESTS | No | Concurrency cap | 8 |
| WAGGLE_REQUEST_TIMEOUT_SECONDS | No | Per-request timeout in seconds | 30 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Abhigyan-Shekhar/Waggle-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server