MCP Gateway & Registry is a governed control plane that provides one authenticated entry point for MCP servers, AI agents, skills, and other AI assets, while supporting discovery, access control, and audit records. Organizations use it to register and manage development tools for autonomous agents and coding assistants. Catalogue add-ons operate or extend workflows around these registered AI assets.
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 agentic-community/mcp-gateway-registry --skill generate-server-cardgit clone --depth 1 https://github.com/agentic-community/mcp-gateway-registryWrote 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/agentic-community/mcp-gateway-registry/generate-server-card)<a href="https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/generate-server-card"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/generate-server-card/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/agentic-community/mcp-gateway-registry/generate-server-card"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/generate-server-card.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 | $0.00052 | $0.02719 |
| Opus 5.5 | $0.00021 | $0.01088 |
| Sonnet 5.5 | $0.00010 | $0.00544 |
| Haiku 4.5 | $0.00005 | $0.00272 |
Grade A, and why
generate-server-card 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 1mo 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate MCP Server Card
Generate an MCP server card JSON file in the mcp-gateway-registry format by analyzing the source code at $ARGUMENTS.
This format is used by https://github.com/agentic-community/mcp-gateway-registry for registering MCP servers in the gateway registry.
Steps
1. Carefully study the source code
Do NOT just skim the top-level files. MCP servers can be complex, multi-file projects. You MUST thoroughly explore the entire folder structure before generating the card.
If $ARGUMENTS is a local folder path, use Glob to find ALL Python files, YAML/JSON configs, and README files in the folder and its subfolders. Read every relevant file.
If $ARGUMENTS is a GitHub URL, use WebFetch to read the raw file contents. Follow imports to discover additional files.
Where to look (MCP servers are not always a single file):
- Entrypoints:
main.py,app.py,server.py,__main__.py,mcp_server.py - Tool definitions: look for
@mcp.tool(),@server.tool(),@tool, tool handler functions, tool registrations - OpenAPI specs:
.jsonor.yamlfiles inopenapi-specs/,specs/,api/folders - these define the tools when an API is exposed as MCP - Config files:
pyproject.toml,requirements.txt,.bedrock_agentcore.yaml,deploy_*.py,docker-compose.yml - Deployment scripts: these reveal the gateway URL, auth scheme, transport type
- Gateway configs:
.deployment_info.json,.roo.json- these have the actual MCP endpoint URL - Sub-folders: check ALL subdirectories for additional tools, resources, or shared utilities
- Resource definitions: MCP servers can expose resources and prompts in addition to tools
From the code, detect:
- Server name: from constants, config files, class names, gateway name
- Description: from docstrings, README, module-level comments, OpenAPI spec info
- Tools: from
@tooldecorators, tool registrations, OpenAPI operationIds, function definitions - Tool schemas: parameter types, required fields, descriptions from function signatures or OpenAPI specs
- Supported transports:
streamable-http,sse,stdio- from server framework config - Auth scheme:
none, bearer JWT, API key, OAuth2, Cognito - from deployment scripts or middleware - MCP endpoint URL: from deployment info, gateway URL, or config files
- Proxy pass URL: the backend URL the gateway proxies to (may differ from the MCP endpoint)
- Version: from constants, pyproject.toml, or default to
1.0.0 - Provider info: organization name and URL if detectable
- License: from pyproject.toml or LICENSE file
- Status:
active,beta, etc.
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.
- 1mo ago First seen · 272 lines · 52 tokens per session scan A ece090d28e88
generate-server-card is a skill published in the GitHub repository agentic-community/mcp-gateway-registry (1,020 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 2,719 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.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Workflow guidance for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files under python/.
security-conductor
Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.