M3
by rafiattrach
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| M3_BACKEND | No | Backend to use: 'duckdb' (default) or 'bigquery' | duckdb |
| M3_DB_PATH | No | Custom path to DuckDB database file (optional) | |
| M3_DUCKDB_MEM | No | DuckDB memory limit per worker (default 3GB) | |
| M3_PROJECT_ID | No | Required for BigQuery backend; Google Cloud project ID | |
| M3_OAUTH2_TOKEN | No | OAuth2 access token | |
| M3_OAUTH2_SCOPES | No | OAuth2 scopes | |
| M3_DUCKDB_THREADS | No | DuckDB threads per worker (default 2) | |
| M3_OAUTH2_ENABLED | No | Enable OAuth2 authentication | |
| M3_OAUTH2_AUDIENCE | No | OAuth2 audience | |
| M3_OAUTH2_ISSUER_URL | No | OAuth2 issuer URL | |
| M3_CONVERT_MAX_WORKERS | No | Number of parallel files for conversion (default 4) |
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/rafiattrach/m3'
If you have feedback or need assistance with the MCP directory API, please join our Discord server