aifp-mcp
by wjabanjj
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port. | 5000 |
| HF_MIRROR | No | Embedding model download mirror. | https://hf-mirror.com |
| CORS_ORIGIN | No | HTTP mode cross-origin whitelist. | * |
| COGNITION_MODE | No | Set to 'local' for local fallback mode, or 'remote' to connect to the enhanced server. Defaults to 'remote'. | remote |
| ANTHROPIC_API_KEY | No | Anthropic API key (alternative for recognizer LLM configuration). | |
| COGNITION_API_KEY | No | Remote mode API key. | |
| COGNITION_DATA_DIR | No | Data storage directory. | ~/.ai-cognition/ |
| COGNITION_LLM_MODEL | No | Recognizer LLM model. | deepseek-chat |
| COGNITION_RECOGNIZER | No | Set to '1' to enable automatic memory recognition. | 0 |
| COGNITION_SERVER_URL | No | Remote algorithm server address (self-hosted). Must be explicitly configured when using remote mode. | |
| COGNITION_LLM_API_KEY | No | Recognizer LLM key (OpenAI compatible). | |
| COGNITION_LLM_BASE_URL | No | Recognizer LLM address. | https://api.deepseek.com |
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
ActivityMaintained
ResponsivenessNo issues