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 gabrielekarra/mcp-anything --skill generategit clone --depth 1 https://github.com/gabrielekarra/mcp-anythingWrote 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/gabrielekarra/mcp-anything/generate)<a href="https://agentmods.dev/skills/gabrielekarra/mcp-anything/generate"><img src="https://agentmods.dev/badge/skills/gabrielekarra/mcp-anything/generate/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/gabrielekarra/mcp-anything/generate"><img src="https://agentmods.dev/badge/skills/gabrielekarra/mcp-anything/generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00066 | $0.00726 |
| Opus 5.5 | $0.00026 | $0.00290 |
| Sonnet 5.5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
generate 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate an MCP server with mcp-anything
mcp-anything (https://github.com/gabrielekarra/mcp-anything) turns a codebase, an API spec, or a
plain-language brief into a working MCP server — Python/FastMCP by default, or TypeScript/mcp-use
with --target mcp-use.
1. Make sure the CLI is current
The MCP ecosystem moves fast; prefer the latest source over a possibly-stale PyPI release:
!command -v mcp-anything >/dev/null 2>&1 && mcp-anything --version || echo "not installed"
If it's missing, install from the repo (not just pip install mcp-anything — PyPI can lag):
pip install --upgrade "mcp-anything[llm] @ git+https://github.com/gabrielekarra/mcp-anything.git"
2. Find out what to expose
Ask only what's missing:
- The source: a local codebase path, or an OpenAPI/GraphQL/gRPC spec (file path or URL).
- What agents should be able to do with it — a sentence or two of use cases is enough for the richer path below.
3. Pick a path
- Quick scan (no use-case framing given):
mcp-anything generate <path-or-url> -o <output-dir> - Recommended — curated, agent-optimized tools (use cases given): write a short domain brief
to a temp YAML file (
server_name,description,use_cases: [...]), then:mcp-anything build --brief <brief.yaml> --data-source <path-or-spec> -o <output-dir> --no-llm— drop--no-llmwhenANTHROPIC_API_KEYis set; grouping and descriptions are noticeably better with it. - Add
--target mcp-useto either command for TypeScript instead of Python.
4. Report back
mcp-anything prints the output directory, tool count, and an MCP client config snippet
(mcpServers: {...}) — surface that, plus how to try it: pip install -e <output-dir> (Python)
or npm install (TypeScript) in the output directory, then add the snippet to the user's client
config.
5. Optional: validate
mcp-anything validate <output-dir> checks the generated server against mcp-anything's own
output contract (tool shape, transport, telemetry, packaging).
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 · 55 lines · 66 tokens per session scan A 54158b281e38
generate is a skill published in the GitHub repository gabrielekarra/mcp-anything (55 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 726 once invoked, about $0.0003 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 2026-09-14.
Other skills, from other repositories
web-reading
Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
skill-creator
A skill for creating or improving reusable instructions for an agent. It covers capturing the intended workflow, writing a draft, testing it, and refining its trigger description.