Personal Agent Memory MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | No | PostgreSQL connection string for the memory database. | postgresql://postgres:postgres@localhost:5432/personal_agent_memory |
| OLLAMA_BASE_URL | No | Base URL of the Ollama server used for embeddings. | http://localhost:11434 |
| OLLAMA_EMBEDDING_MODEL | No | Name of the Ollama embedding model to use. | qwen3-embedding:0.6b |
| MEMORY_REST_API_ENABLED | No | Set to 'true' to enable the simple REST user API. | false |
| MEMORY_DEFAULT_USER_TOKEN | Yes | Token used for authenticating MCP and REST API requests. Must be a random string of at least 32 characters. | |
| MEMORY_EMBEDDING_DIMENSION | No | Dimension of the embedding vectors. Must match the database schema (e.g. vector(1024)). | 1024 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_turnC | Store one interaction as candidate durable memory. |
| get_contextB | Retrieve compact durable memory context for the caller input. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one stores a turn for potential durable memory, the other retrieves context. There is no ambiguity between writing and reading operations.
Both tool names follow the consistent verb_noun pattern: ingest_turn and get_context. The naming is clear and predictable.
With only 2 tools, the server is on the thin side for a full memory system, but it covers the basic store/retrieve workflow. It feels borderline for its stated purpose.
The memory domain typically requires update, delete, and list operations in addition to ingest and retrieve. The absence of these leaves significant gaps that could hinder agents needing to manage durable memory effectively.