A
licenseNot graded
qualityB
maintenanceA public-safe research prototype for controlling AI-agent tool actions with deterministic policy, risk-based human approval, time-bound authorization and a tamper-evident audit chain.
MIT
geomed_copilot
The server provides access to GeoMed capabilities, case listing, and radiograph analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@geomed_copilot Measure and verify the hallux valgus angle"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RadMeasure
A medical measurement agent with controlled verification and repair.
HRNet landmarks · Vision-language models · KEEP / REPAIR / STOP
Overview · Architecture · Getting Started · Documentation
Overview
RadMeasure measures hallux valgus angle (HVA) and intermetatarsal angle (IMA) from foot radiographs. An HRNet landmark model and a vision-language model inspect the image independently; a LangGraph controller checks their agreement and decides whether to accept, recheck, or request human review.
Simple web interface — upload an image and choose GPT, Claude, or Gemini.
Protocol-constrained actions — model requests are limited to registered definitions and tools.
Bounded repair — the VLM rechecks the image within an explicit retry budget.
Traceable decisions — retain estimates, verification reasons, and review history.
Related MCP server: signet-eval
Architecture
Accepted measurements come from landmark geometry. Repair revises the VLM estimate, not the landmark coordinates. Agreement alone does not establish accuracy.
Getting Started
pip install -e '.[api,prod,vision,inference]'Follow the setup guide to configure the landmark checkpoint, comparison policy, and app access key. Start the API and worker in separate terminals:
uvicorn radmeasure.api:create_app --factory --host 127.0.0.1 --port 8000
radmeasure-workerOpen http://127.0.0.1:8000, upload an image, and enter your selected provider's Model ID and API key. Checkpoints and credentials are not bundled.
Workflow & configuration · Controller source · Provider adapters · Contributing
Research prototype; not validated for clinical use.
Available Tools
3 toolsanalyze_radiographB
Run geometry checks, retrieval, citations, and tool traces for a configured case ID.
Inputs: image_id (required), top_k, question.
list_available_casesC
List case identifiers accepted by the configured backend.
Inputs: limit.
list_geomed_capabilitiesA
Describe the GeoMed backend, measurements, and limitations.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.6/5.0
Scored across 3 tools
Disambiguation5/5
Each tool serves a clearly distinct purpose: describing backend capabilities, listing available cases, and analyzing a specific radiograph. There is no overlap in functionality, making misselection unlikely.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern: list_geomed_capabilities, list_available_cases, analyze_radiograph. The naming is uniform and predictable.
Tool Count5/5
With only 3 tools, the set is tightly scoped for the stated purpose of interacting with a GeoMed backend for case analysis. Each tool earns its place, and the count is appropriate—neither too sparse nor excessive.
Completeness5/5
The tool surface covers the full expected workflow: understanding the backend's capabilities, selecting a case, and performing the analysis (which includes retrieval and citations). No additional operations seem necessary for the apparent read-only analysis domain.
Maintenance
ActivitySlowing
ResponsivenessNo recent community issues
Related MCP Connectors
Machine-verifiable authorization checks for autonomous AI agents.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Policy-aware AI execution, verification, cost, and trajectory evidence for agents.
Runtime permission, approval, and audit layer for AI agent tool execution.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceDeterministic policy enforcement for AI agent tool calls. It evaluates every tool call against user-defined rules before execution, with no LLM in the authorization path.4MIT
- AlicenseNot gradedqualityCmaintenanceGates agent tool execution with human approval, audit trails, and replay-resistant permits, enabling safe use of tools in agent loops.MIT
- AlicenseNot gradedqualityCmaintenanceProvides permission gates and tamper-evident audit logging for AI agent tool executions, with declarative policies, consent ladders, and hash-chained verification.MIT