ner-mcp-fr
by athoune
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NER_DEVICE | No | ONNX runtime provider: auto, cpu, or cuda. | auto |
| NER_OFFLINE | No | Set to 1 to disable all network access. | 0 |
| NER_PRELOAD | No | Set to 1 to load the model at startup. | 0 |
| NER_THREADS | No | Number of onnxruntime threads. | |
| NER_MODEL_ID | No | Source of the tokenizer and label table. | CATIE-AQ/NERmembert-base-4entities |
| NER_CACHE_DIR | No | Alternative Hugging Face cache directory. | |
| NER_LOG_LEVEL | No | Log level written to stderr; stdout is reserved for the MCP protocol. | INFO |
| NER_MIN_SCORE | No | Default confidence threshold for entities. | 0.0 |
| NER_ONNX_PATH | No | Local ONNX file path; bypasses downloading. | |
| NER_BATCH_SIZE | No | Number of windows processed per pass. | 8 |
| NER_ALLOWED_DIRS | No | Colon-separated list of directories allowed for ner_extract_file. | |
| NER_ARTIFACT_FILE | No | Weight file within the artifact repository. | model-fp16.onnx |
| NER_ARTIFACT_REPO | No | Hugging Face repository containing the ONNX weights. | athoune/ner-mcp-fr-onnx |
| NER_MAX_INPUT_CHARS | No | Input size guard, also bounds file size for file extraction. | 200000 |
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 recent community issues