MCP Toolsets Runtime
A shared runtime that discovers LangChain tools from a toolset package and serves them as an MCP server, with optional UI views and a CLI for managing tools.
README
mcp-toolsets-runtime
The shared runtime for MCP Toolsets.
Both developmentseed/mcp-toolsets and downstream repos generated from it
(e.g. ecmwf/dss-agentic-ai-services) install this package instead of each
carrying their own copy of the runtime.
What's in here
One Python distribution (mcp-toolsets-runtime) exposing three top-level
modules, plus the view-side JS bridge:
| Module | What it is |
|---|---|
mcp_runtime |
Discovers a toolset's LangChain tools (TOOLS) and serves them as an MCP server; serves UI views (VIEWS) as ui:// resources; derives server instructions from CREDENTIAL_HEADERS. Entry points: mcp-serve, mcp-index. |
mcp_cli |
Typer CLI to list and call tools on a running MCP service. Entry point: mcp-cli. |
mcp_toolset |
Scaffolds a new toolset in a consumer repo (mcp-toolset new [--with-ui] <name>), wired to this package + the npm view bridge. |
mcp_agent |
Example Chainlit chat agent that discovers MCP servers behind an index URL and drives their tools. Ships the Chainlit host element elements/McpView.jsx. Entry points: mcp-agent, mcp-agent-web. Requires the [agent] extra. |
@developmentseed/mcp-view (js/mcp-view) |
The view-side ui/* postMessage bridge a toolset UI imports (onData / sendMessage). Published to npm separately. |
The toolset plugin contract
mcp_runtime discovers a toolset purely by convention — a <toolset>.tools
module exporting:
TOOLS— a non-empty list of LangChain tools that return aToolResult.VIEWS(optional) —{tool_name: view_id}, with a built bundle at<package>/views/<view_id>.html.CREDENTIAL_HEADERS(optional) — header names the tools read off the transport; used to derive the model-facing auth hint.
Treat these, ToolResult, and the ui/* wire protocol as public API.
Install
# base: runtime + cli (lean, for tool-serving images)
pip install "mcp-toolsets-runtime @ git+https://github.com/developmentseed/mcp-toolsets-runtime.git@v0.1.0"
# with the Chainlit web agent
pip install "mcp-toolsets-runtime[agent] @ git+https://github.com/developmentseed/mcp-toolsets-runtime.git@v0.1.0"
With uv, as a consumer:
dependencies = ["mcp-toolsets-runtime[agent]"]
[tool.uv.sources]
mcp-toolsets-runtime = { git = "https://github.com/developmentseed/mcp-toolsets-runtime.git", tag = "v0.1.0" }
Imports are unchanged from the old workspace packages: from mcp_runtime.server import build_server, etc. Bump the runtime by changing the tag and running
uv lock.
Consuming this package — the plugin contract, serving toolsets, wiring up UI
views (including mcp-agent install-elements and the npm bridge), and migrating
off the in-repo workspace: see docs/CONSUMING.md.
Develop
uv sync --all-extras # install with [agent] + dev tools
./scripts/lint # ruff check + ruff format --check + mypy (config in pyproject)
./scripts/test # pytest
./scripts/build-js # typecheck + build + vitest for js/mcp-view (needs node)
Releases
Versioning and CHANGELOG.md are managed by
release-please from Conventional
Commits. See CONTRIBUTING.md — in short, your PR title is
the changelog entry, and CI fails a PR whose title isn't a valid conventional
commit. The Python package and the JS bridge share one version (linked).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.