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 developmentseed/mcp-toolsets-runtime --skill skillgit clone --depth 1 https://github.com/developmentseed/mcp-toolsets-runtimeWrote 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/developmentseed/mcp-toolsets-runtime/skill)<a href="https://agentmods.dev/skills/developmentseed/mcp-toolsets-runtime/skill"><img src="https://agentmods.dev/badge/skills/developmentseed/mcp-toolsets-runtime/skill/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/developmentseed/mcp-toolsets-runtime/skill"><img src="https://agentmods.dev/badge/skills/developmentseed/mcp-toolsets-runtime/skill.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 | $0.00072 | $0.01959 |
| Opus 5.5 | $0.00029 | $0.00784 |
| Sonnet 5 | $0.00014 | $0.00392 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade A, and why
writing-mcp-toolsets scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `requests`, `urllib` | `httpx.AsyncClient` | How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a toolset
A toolset is a Python package that exports a list of LangChain tools. The runtime imports it by name and serves it over MCP.
This file is the procedure. The detail lives in the mcp-toolsets-runtime
documentation: CONSUMING for the contract, SESSION-STATE for stored values. A
marker like (#4c) below means that section of CONSUMING. Read those for
detail; this file does not reproduce them.
Get these right first
They are cheap now and expensive later.
1. The consuming repo owns no runtime code. mcp_runtime, mcp_state,
mcp_cli, mcp_agent, mcp_agent_api and mcp_toolset come from the
mcp-toolsets-runtime package. Never add a module under one of those names,
and never patch runtime behaviour locally. If the runtime is wrong, fix it in
the runtime, release it, and bump the pin.
2. Data key names are public. Every key in a tool's return except
message is stored as <toolset>/<tool>/<field>. The agent's model reads that
name when it decides which stored value to pass into a later call, and that
call may land in a different toolset. The key is the only thing the two share:
no types, no imports, no registry.
So name the thing, not its type. area_of_interest is a good key; geometry
is a bad one, because a coverage footprint is also a geometry and the two are
identical JSON. A model handed the wrong one produces confident nonsense and
nothing will notice. (#4c)
3. Scaffold, never hand-roll. mcp-toolset new writes the package, the
test, the pyproject and whatever deployment config the repo declares. A
hand-made directory misses files you will not notice until deploy.
Steps
1. Scaffold
uv run mcp-toolset new my-toolset # --with-ui to add a React view
This writes toolsets/my-toolset/ containing src/my_toolset/tools.py, a
test, a pyproject, and the deployment file the repo's root pyproject declares
under [tool.mcp-toolset] deployment-config.
2. Write the tools
tools.py must export TOOLS, a non-empty list. Two exports are optional:
VIEWS maps a tool name to a view id, and CREDENTIAL_HEADERS lists the HTTP
headers the tools read. (#2)
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.
- 7d ago First seen · 195 lines · 72 tokens per session scan A e877e7ba1b35
writing-mcp-toolsets is a skill published in the GitHub repository developmentseed/mcp-toolsets-runtime (0 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,959 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…