trm-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRM_DATA_DIR | No | Override the default data directory (default: ${XDG_DATA_HOME:-~/.local/share}/trm-mcp) | |
| HF_HUB_OFFLINE | No | Set to 1 to enable Hugging Face offline mode | |
| TRM_QDRANT_URL | No | URL for Qdrant service (example: http://127.0.0.1:6333) | |
| TESSDATA_PREFIX | No | Path to Tesseract tessdata directory | |
| TRM_PARSE_WORKERS | No | Number of PDF parse worker processes (default: 8) | |
| TRM_PARSE_PIN_CPUS | No | Set to 1 to pin parse worker processes to CPU cores, 0 to disable | |
| TRM_QDRANT_STORAGE | No | Override the storage location for Qdrant vectors (default: .trm-data/qdrant/ under the data directory) | |
| TRANSFORMERS_OFFLINE | No | Set to 1 to enable Transformers offline mode | |
| TRM_VISUAL_BATCH_MIN | No | Minimum batch size for visual encoding during OOM backoff (default: 1) | |
| TRM_PARSE_ORT_THREADS | No | ONNX Runtime intra-op threads per parse worker (default: 2) | |
| TRM_VISUAL_BATCH_SIZE | No | Starting batch size for visual encoding (default: 8; automatically reduces on OOM) |
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 |
|---|---|
| list_documentsB | List indexed documents and their stable IDs, titles, page counts, and status. |
| searchB | Hybrid BM25/dense/visual retrieval with local reranking and page citations. |
| grepC | Find exact register, field, signal, address, or regex occurrences by page. |
| readB | Read up to 20 indexed pages as Markdown, text, HTML, or layout JSON. |
| renderA | Render one to four PDF pages as images for visual inspection. |
| compareA | Retrieve matching passages from two documents and return aligned unified diffs. |
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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/strongtz/trm-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server