Toolc MCP server
dev.toolc/toolc·v0.1.1Optimizing compiler for agent tools: many MCP servers or REST APIs in, one lean endpoint out.
0 stars
Reviews
Write oneNobody has reviewed Toolc yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Toolc tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it
- Code scan6 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 18 days ago15/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How Toolc compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 4,460 AI and agents servers
Install Toolc in Claude Code, Cursor or VS Code
Runs npx -y @toolc/cli on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add toolc -- npx -y @toolc/cli
What the publisher says
From the Toolc repository's README, as published. We do not edit it. Read it on GitHub
toolc
The optimizing compiler for agent tool surfaces. Point it at your MCP servers, or just a REST API's OpenAPI spec, or even a docs page, and get back one endpoint that serves a smaller, smarter tool surface: cheaper for every agent that connects, more accurate on every task, with every call logged.
Connecting N MCP servers dumps every tool definition into the model's context, degrades tool selection, and forces improvised multi-hop call chains. toolc compiles the federation instead:
merge into single facade tools with deterministic routing
- Rewrite: LLM-optimized descriptions with sibling disambiguation
- Consolidate: families of near-duplicate tools (searchx/findx/get_x)
(searchtools/calltool) when you want maximum context savings
- Selection: the whole catalog compresses behind two meta-tools
identifiers and sourcing details
- Compaction: oversized results are summarized at serve time, preserving
a drafted spec synthesized from their documentation
- Compose: REST APIs join the pool straight from an OpenAPI spec, or from
cluster into recommended fixes
- Observe: every call logged with arguments and results; recurring errors
Benchmark
131 tools across 5 live servers, 30 tasks × 3 trials, judged answers (full grid · consolidation run):
Consolidation dominates both ends of the frontier: the selection surface is the cost lever, consolidation lifts accuracy everywhere. Every pass is a config toggle; pick the tradeoff per deployment.
Quick start
git clone https://github.com/toolc-dev/toolc && cd toolc
pnpm install && pnpm -r test
# describe your federation
cp toolc.config.example.jsonc toolc.config.jsonc
# introspect it
node packages/cli/bin/toolc.mjs -c toolc.config.jsonc inspect
# compile (set ANTHROPIC_API_KEY for the rewrite/consolidate passes)
node packages/cli/bin/toolc.mjs -c toolc.config.jsonc compile
# serve the compiled surface over stdio (add to Claude as an MCP server)
node packages/cli/bin/toolc.mjs -c toolc.config.jsonc serve --mode compiledA downstream can be an MCP server or a bare REST API:
{
"downstream": [
{ "id": "gh", "transport": { "type": "http", "url": "https://api.githubcopilot.com/mcp/" } },
{ "id": "nws", "transport": { "type": "openapi", "spec": "https://api.weather.gov/openapi.json" } }
]
}See SELF_HOSTING.md for Docker deployment.
Hosted
toolc.dev runs this same engine as a managed service: compiled HTTPS endpoints, a console with a playground and full-payload log explorer, docs-to-spec drafting, and error-driven fix recommendations.
Layout
- packages/core: IR (Capability Graph), frontends (MCP, OpenAPI, docs synthesis), passes, emit
- packages/gateway: runtime MCP server (mirror + compiled) with call logging and compaction
- packages/cli: the toolc command
- packages/harness: benchmark runner, grading, reports
- packages/shared: config schema, errors
License
The engine (everything in this repository) is Apache-2.0, forever: anyone can compile and serve their own tool surfaces locally with the exact same compilation quality as the hosted product.
Nothing above is checked by us. What we check is on the safety report.
Toolc: common questions
- Is Toolc MCP server safe?
- Mostly: it is graded B (80/100). Read the Toolc safety report
- How do I install Toolc?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Toolc need an API key?
- Yes. The registry entry asks for
ANTHROPIC_API_KEY. - Is Toolc maintained?
- The last commit was 50 days ago (2026-09-15). The latest release is v0.1.1.
- What can I use instead of Toolc?
- Servers from other publishers that do the same job: DCC-MCP Core MCP server, Mockserver MCP server and Lm MCP server.
Alternatives to Toolc
Same job from other publishers: the closest match first, then the best rated.
- DCC-MCP CoreAgent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.not reviewedEstablishedA
- MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.not reviewedEstablishedA
LmConnect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.not reviewedEstablishedA