Azure/gpt-rag-mcp is a Python server that exposes GPT-RAG capabilities through the Model Context Protocol. It is deployed with Azure resources and consumed by GPT-RAG through its MCP strategy, while the catalogue provides instructions, skills, and agents for operating it.
Borrowing it
Nothing to install: this file belongs to Azure/gpt-rag-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure/gpt-rag-mcp/main/.github/skills/mcp-capability-development/SKILL.mdgit clone --depth 1 https://github.com/Azure/gpt-rag-mcpWrote 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/azure/gpt-rag-mcp/mcp-capability-development)<a href="https://agentmods.dev/skills/azure/gpt-rag-mcp/mcp-capability-development"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag-mcp/mcp-capability-development/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/azure/gpt-rag-mcp/mcp-capability-development"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag-mcp/mcp-capability-development.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 | $0.00038 | $0.00342 |
| Opus 5.5 | $0.00015 | $0.00137 |
| Sonnet 5.5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
mcp-capability-development 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 2mo 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.
What it actually says
MCP capability development
- Classify the capability as a tool, resource, prompt, or transport concern
and confirm
Azure/gpt-rag-mcpowns it. - Identify the orchestrator outcome, trust boundary, authorization model, external effects, limits, and compatibility constraints.
- Define a narrow typed contract: name, description, arguments, defaults, validation, result shape, error behavior, and bounds.
- Put focused logic in
src/tools/,src/resources/, orsrc/prompts/and keep registration insrc/server.pythin. - Treat all inputs and upstream content as untrusted. Validate schemes, hosts, identifiers, paths, sizes, and counts before effects.
- Add timeouts, output limits, least-privilege access, and actionable non-sensitive errors at external boundaries.
- Preserve compatibility or document and coordinate migration with the
orchestrator and
Azure/GPT-RAG. - Add focused behavior or contract tests when feasible.
- Restore with
uv sync, check import or startup behavior, exercise the capability with the MCP Inspector, and run orchestrator end to end when the integration contract changes. - Update this repository's documentation and the GPT-RAG docs branch when users or operators observe the change.
Never place this runtime capability under .github/; that directory contains
engineering-time Copilot assets only.
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.
- 2mo ago First seen · 31 lines · 38 tokens per session scan A 7e04cc206ec1
mcp-capability-development is a skill published in the GitHub repository Azure/gpt-rag-mcp (22 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 342 once invoked, about $0.0002 per session on Opus 5.5. 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.
mcp-capability-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-capability-developmentAzure/gpt-rag-mcp | Skill | 22 | 10d ago | MIT | A | 38 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |