CtrlK
BlogDocsLog inGet started
Tessl Logo

deploying-openmed-mcp

Run OpenMed's Model Context Protocol (MCP) server so coding agents (Claude Code, Codex) and chat clients can call clinical NER, PII extraction, and de-identification as tools, on-device. Use when the user wants to add OpenMed to an agent's MCP config, expose de-id/NER as MCP tools, run an MCP server over stdio or Streamable HTTP, give Claude/Codex access to OpenMed, or containerize the MCP server. Covers the mcp extra, create_mcp_server, the 7 tools (openmed_analyze_text, openmed_extract_pii, openmed_deidentify, openmed_list_models, openmed_list_pii_languages, openmed_loaded_models, openmed_unload_model), the resources and prompts, stdio vs streamable-http transports, ServiceRuntime env config, and MCP client config snippets.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable deployment guide with executable commands, a tool table, config snippets, and a Dockerfile. Its main weaknesses are some repeated PHI guidance and implicit rather than explicit validation checkpoints in the workflow.

Suggestions

Add explicit verification checkpoints to the workflow (e.g., after launch confirm the server is up, and after registration confirm the 7 tools/resources appear) to lift workflow clarity.

Dedupe the PHI/trust-boundary guidance so it lives once in 'Edge cases & gotchas' rather than recurring across 'When to use', the workflow, and edge cases.

Move the full Dockerfile and/or the detailed tool-arg table into reference files to keep SKILL.md a leaner overview.

DimensionReasoningScore

Conciseness

Mostly lean with executable commands, a dense tool table, and code blocks, but carries some repetition (PHI/trust-boundary guidance recurs across 'When to use', the workflow, and 'Edge cases') and minor over-explanation that could be trimmed.

4 / 5

Actionability

Fully executable and copy-paste ready: pip install, server launch with transport flags, embed snippet, .mcp.json config, env vars with defaults, a Dockerfile, and a tool-args table covering stdio, HTTP, embed, Docker, and client-config cases.

5 / 5

Workflow Clarity

A clear 6-step sequence (install+launch, configure runtime, register, front HTTP with auth/TLS, call tools, manage memory) with specific commands, but explicit validation checkpoints (e.g., verify the server started or the 7 tools appeared before proceeding) are implicit rather than stated.

4 / 5

Progressive Disclosure

No bundle files exist; the body is a single well-organized SKILL.md with clearly signaled one-level sections and easy navigation, though the full Dockerfile and detailed arg table could be offloaded to reference files to slim the overview.

4 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete actions, explicit 'Use when...' triggers, and a distinct product-scoped niche. Trigger term coverage is very good but could be pushed further with additional synonyms and file/config extensions to reach the top anchor.

Suggestions

Add a few more natural synonyms/extensions (e.g., 'MCP server', '.mcp.json', 'FastMCP') to broaden trigger-term coverage toward the top anchor.

Consider trimming the long 'Covers...' inventory clause, which leans toward verbosity; the core what+when already carries the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (run the MCP server, expose de-id/NER as tools, add to agent MCP config, run over stdio/Streamable HTTP, containerize) and enumerates the 7 tools and components, giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly states what it does (runs an on-device MCP server exposing clinical NER/PII/de-id tools) and provides a clear 'Use when...' clause with multiple concrete trigger phrases, answering both what and when.

5 / 5

Trigger Term Quality

Includes natural user phrasings like 'add OpenMed to an agent's MCP config', 'expose de-id/NER as MCP tools', and 'give Claude/Codex access to OpenMed' with product names and transport synonyms, but stops short of the broad synonym/extension spread of the top anchor.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to OpenMed's MCP server deployment with a named product, specific tool surface, and transport choices, creating a clear niche with minimal overlap risk against other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.