medeval-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEDEVAL_BASE_URL | Yes | Base URL of the MedEval backend (e.g., http://127.0.0.1:8000 or a trusted LAN address like http://192.168.0.166:8001). | http://127.0.0.1:8000 |
| MEDEVAL_API_TOKEN | No | API token issued by MedEval, sent as X-API-Token. Required only if MedEval has token authentication enabled. | |
| MEDEVAL_BEARER_TOKEN | No | Alternative signed browser/session token for authentication. Use instead of MEDEVAL_API_TOKEN when applicable. | |
| MEDEVAL_PROJECT_ROOT | Yes | Filesystem root of the MedEval project workspace. | |
| MEDEVAL_ALLOWED_FILE_ROOTS | Yes | Semicolon-separated list of allowed local upload roots (e.g., C:\path\to\medeval;C:\path\to\materials). | |
| MEDEVAL_ALLOW_PRIVATE_NETWORK | No | Set to 'true' to allow connections to private IP addresses (e.g., a trusted LAN backend). | false |
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 |
|---|---|
| medeval_healthA | Check the local backend and return a bounded capability summary. |
| medeval_list_projectsB | List local chat projects/workspaces; use before selecting a workspace. |
| medeval_create_workspaceA | Create an isolated workspace only after an explicit user request. |
| medeval_get_workspaceB | Read a selected workspace summary and integrity counters. |
| medeval_list_workspace_documentsA | List generated/versioned document heads in one workspace. |
| medeval_list_runsB | List observable workflow runs and agent progress for one workspace. |
| medeval_get_runC | Read agents, actions, retrievals, warnings, and outputs for one run. |
| medeval_get_agent_contextC | Read the bounded context receipt for one agent in a selected run. |
| medeval_list_project_documentsB | List raw and retrieved documents in one project evidence repository. |
| medeval_search_project_evidenceC | Search bounded local evidence; inspect sources before factual use. |
| medeval_build_section_contextB | Build a bounded, section-scoped evidence pack for one CEP/CER section. |
| medeval_ingest_materialsB | Upload allowed local files into a new immutable cleaning session. |
| medeval_list_generation_templatesA | List generation templates installed in the local MedEval backend. |
| medeval_start_generationC | Start generation after explicit authorization; segmented generation is the safe default. |
| medeval_start_evaluationC | Start evaluation only after explicit authorization. |
| medeval_get_task_progressB | Read a lightweight live status snapshot without resubmitting the task. |
| medeval_get_generation_taskB | Read generation progress, output metadata, and adopted artifacts. |
| medeval_list_document_revisionsA | List immutable revisions and the current head for one document. |
| medeval_read_document_revisionB | Read a bounded page of one immutable Markdown revision. |
| medeval_diff_document_revisionsA | Compare two immutable revisions with a bounded textual diff. |
| medeval_patch_document_revisionB | Append one optimistic-lock revision; never overwrite revision history. |
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 21 tools
Tools generally have distinct purposes, but there is some overlap between get_run, get_task_progress, and get_generation_task, which could confuse an agent. Descriptions help clarify, but the boundaries are not perfectly crisp.
All tools share the 'medeval_' prefix and use a consistent snake_case verb_noun pattern (e.g., list_projects, create_workspace, read_document_revision). The one exception, medeval_health, is a minor deviation but does not break overall consistency.
21 tools is slightly heavy but justified given the broad domain covering workspaces, projects, evidence, generation, evaluation, and revisions. The count is within a reasonable range for such a server.
The tool surface covers most core workflows, but there are notable gaps: no workspace update/delete, no get_project, and no cancel/stop operations for generation or evaluation. These are gaps an agent might hit, though the main paths are present.