turing_AgentMemory_MCP
by chetto1983
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EMBED_MODEL | Yes | Model name for embeddings | |
| GLINER_MODEL | No | GLiNER model name | |
| RERANK_BLEND | No | Enable reciprocal-rank blending (set to '1') | |
| RERANK_MODEL | No | Model name for reranking | |
| TURINGDB_URL | Yes | URL of the TuringDB daemon | |
| EMBED_API_KEY | No | API key for the embedding provider (overrides PROVIDER_API_KEY) | |
| GLINER_LABELS | No | Comma-separated list of entity labels | |
| GLINER_REDACT | No | Set to '1' to redact entity spans before storage | |
| TURINGDB_HOME | Yes | Shared TuringDB home directory path | |
| EMBED_BASE_URL | Yes | Base URL for the embedding provider | |
| GLINER_BACKEND | No | GLiNER backend: 'auto', 'gliner', 'gliner2_onnx', etc. | |
| GLINER_ENABLED | No | Set to '1' to enable GLiNER entity extraction | |
| RERANK_API_KEY | No | API key for the rerank provider (overrides PROVIDER_API_KEY) | |
| RERANK_BASE_URL | No | Base URL for the rerank provider | |
| EMBED_DIMENSIONS | Yes | Dimensionality of the embedding vectors | |
| GLINER_PRECISION | No | Precision setting for GLiNER | |
| GLINER_PROVIDERS | No | Provider list for GLiNER | |
| GLINER_THRESHOLD | No | Threshold for entity detection | |
| PROVIDER_API_KEY | No | Shared API key for embedding and rerank providers | |
| RERANK_THRESHOLD | No | Threshold score for rerank filtering | |
| RERANK_DIMENSIONS | No | Dimensionality for rerank (if needed) | |
| EMBED_TIMEOUT_SECONDS | No | Timeout in seconds for embedding requests | |
| AGENTMEMORY_AUTH_TOKEN | No | Single static bearer token for MCP auth | |
| RERANK_TIMEOUT_SECONDS | No | Timeout in seconds for rerank requests | |
| AGENTMEMORY_AUDIT_JSONL | No | Path to audit JSONL file (e.g., /turing/audit/agentmemory.jsonl) | |
| AGENTMEMORY_AUTH_SCOPES | No | Scopes for auth | |
| AGENTMEMORY_AUTH_TOKENS | No | Comma-separated list of tokens for rotation | |
| PROVIDER_API_KEY_HEADER | No | Custom header for API key (e.g., x-api-key) | |
| PROVIDER_API_KEY_SCHEME | No | Custom scheme for API key (e.g., Bearer) | |
| AGENTMEMORY_UTCP_AUTH_ENV | No | Auth environment variable name for UTCP manual | |
| AGENTMEMORY_AUTH_CLIENT_ID | No | Client ID for auth metadata | |
| RERANK_PRESERVE_SEED_MARGIN | No | Margin to preserve top seed rank (default 0.05) | 0.05 |
| AGENTMEMORY_UTCP_MCP_COMMAND | No | MCP command JSON array for UTCP manual | |
| AGENTMEMORY_UTCP_SERVER_NAME | No | Server name for UTCP manual | |
| AGENTMEMORY_REDACTION_ENABLED | No | Set to '1' to enable pattern redaction before persistence | |
| AGENTMEMORY_OBSERVABILITY_JSONL | No | Path to observability spans JSONL file | |
| AGENTMEMORY_AUTH_REQUIRED_SCOPES | No | Required scopes for auth |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues