OpenMed is local-first healthcare AI software that extracts clinical information and removes personally identifying details from clinical text on hardware controlled by the user. Healthcare developers use its Python runtime, Apple Silicon and mobile SDKs, and browser support for on-device clinical NER and PII de-identification.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add maziyarpanahi/openmed --skill deploying-openmed-mcpgit clone --depth 1 https://github.com/maziyarpanahi/openmedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/maziyarpanahi/openmed/deploying-openmed-mcp)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/deploying-openmed-mcp"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/deploying-openmed-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/deploying-openmed-mcp"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/deploying-openmed-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00186 | $0.02065 |
| Opus 5 | $0.00093 | $0.01033 |
| Sonnet 5 | $0.00037 | $0.00413 |
| Haiku 4.5 | $0.00019 | $0.00206 |
Grade A, and why
deploying-openmed-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying the OpenMed MCP server
openmed.mcp.server exposes OpenMed's clinical NLP as Model Context Protocol
tools, so coding agents (Claude Code, Codex) and chat clients can de-identify and
analyze clinical text by calling tools instead of writing glue code. It runs
on-device — models are local, no telemetry — and the server instructs
clients to send real PHI only to instances the user operates.
When to use this skill
When an agent or LLM client should be able to invoke OpenMed: add it to a
coding agent's MCP config, give a chat client de-id/NER tools, or run a shared
MCP endpoint for a team. For programmatic HTTP from your own services, prefer
serving-openmed-rest-api; for corpora, batch-processing-clinical-text.
Quick start
pip install "openmed[mcp]" # FastMCP / MCP SDK
# stdio transport (what coding agents spawn): default
python -m openmed.mcp.server
# Streamable HTTP transport (network-reachable):
python -m openmed.mcp.server --transport streamable-http --host 127.0.0.1 --port 8081
# Or embed it:
from openmed.mcp.server import create_mcp_server
server = create_mcp_server() # FastMCP("OpenMed", ...) with tools+resources+prompts
server.run(transport="stdio") # or "streamable-http"
CLI flags (build_arg_parser): --transport {stdio,streamable-http,http},
--host, --port, --streamable-http-path (default /mcp), --version.
Env equivalents: OPENMED_MCP_TRANSPORT, OPENMED_MCP_HOST,
OPENMED_MCP_PORT (8081), OPENMED_MCP_PATH.
The 7 tools (confirmed in openmed/mcp/server.py)
| Tool | What it does | Key args |
|---|---|---|
openmed_analyze_text |
clinical NER | text, model_name (disease_detection_superclinical), confidence_threshold, group_entities, aggregation_strategy, sentence_*, keep_alive |
openmed_extract_pii |
detect PII/PHI spans | text, model_name (default PII model), confidence_threshold (0.5), use_smart_merging, lang, normalize_accents |
openmed_deidentify |
mask/remove/replace/hash/shift dates | text, method (mask), confidence_threshold (0.7), keep_year, shift_dates, date_shift_days, keep_mapping, lang |
openmed_list_models |
list registry models | category, pii_language, limit |
openmed_list_pii_languages |
supported PII languages + default models | — |
openmed_loaded_models |
resident-model status of the MCP runtime | — |
openmed_unload_model |
free one model or all inactive models | model_name, all_models |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 161 lines · 186 tokens per session scan A ae9c1286fdac
deploying-openmed-mcp is a skill published in the GitHub repository maziyarpanahi/openmed (5,302 stars, last pushed today), licensed Apache-2.0. It adds 186 tokens to every session and 2,065 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-new-model
Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face modeltype to a new file under mlxvlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing model, adding a test class, and validating the port. Covers vision-language…
benchmarking
Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, parameter sweeps, and self-contained reproducible bench scripts to paste into a…
cli-inference
Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlxvlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors around processors, prompts, model loading, or missing weights.
contributing
Use this skill when the user wants to contribute to MLX-VLM — opening a PR, where model code/config/tests go, backward-compatible config args, running the test suite, code formatting and the pre-commit hooks (black, clang-format), and PR expectations (tests, review, perf evidence). Use it to set up a change so it…
convert-quantize
Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlxvlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts, calibration (text or multimodal), local vs Hub paths, revisions, uploading to…
reproducible-github-issues
Use this skill when the user wants to create, improve, or triage a reproducible GitHub issue for MLX-VLM, including bug reports from CLI inference, server inference, model loading, processors, media inputs, dependency setup, crashes, wrong outputs, or performance regressions.