Toolroute

io.github.grossiwebPublished by GitHub account grossiwebv0.2.2Updated Oct 24, 2026

Route AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

ToolRoute recommends the best MCP server and LLM model for a given task, scored on benchmark executions, so an assistant can pick tools and models before acting

What you can do
Route a task to a recommended MCP server plus LLM model, or to a model only, with confidence, alternatives and fallback options and cost estimates per model. Classify compound tasks into an ordered multi-tool orchestration chain. Search the MCP server catalog and check service health and public aggregate metrics. Report execution outcomes and model output quality back to the service, and register agent identity or set routing preferences.
When to use it
Useful when an assistant must choose among many MCP servers or LLM models and wants a scored recommendation with cost estimates, or when a compound task needs an ordered tool chain. Less useful if you already know which tool and model to use.
Requirements
The README shows a remote endpoint added to an MCP client, or the npm SDK package installed locally; the manifest lists a local stdio process. Network access to the hosted service is needed. No API keys or environment variables are declared for normal use; self-hosting needs Supabase variables.
Before you install
Routing sends your task text to a third-party hosted service, which also runs an LLM classifier on it. Reporting and telemetry endpoints send execution outcomes and skill identifiers back to the service, and outcomes update shared scores. Self-hosting requires Supabase credentials, including a service role key. Routing calls incur small per-call costs.

Installation

In SourceWeft

  1. Open Toolroute in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ToolRoute

Routing layer for AI agents. One call returns the best MCP server and LLM for any task — scored on 132 real benchmark executions.

[MIT]

Quick start

Add to any MCP client (Claude Code, Cursor, Windsurf, Cline):

json
{  "mcpServers": {    "toolroute": {      "url": "https://toolroute.io/api/mcp"    }  }}

Or via HTTP:

bash
curl -X POST https://toolroute.io/api/route \  -H "Content-Type: application/json" \  -d '{"task": "search the web for recent AI papers"}'
json
{  "approach": "mcp_server",  "recommended_skill": "exa-mcp-server",  "recommended_skill_name": "Exa MCP Server",  "recommended_model": {    "slug": "claude-haiku-4-5-20251001",    "display_name": "Claude Haiku 4.5",    "provider": "anthropic",    "tier": "cheap_chat",    "provider_model_id": "anthropic/claude-haiku-4-5-20251001",    "input_cost_per_mtok": 1.00,    "output_cost_per_mtok": 5.00  },  "confidence": 0.91,  "alternatives": ["brave-search-mcp", "tavily-mcp"],  "fallback": "brave-search-mcp"}

recommended_model is always an object, not a bare string — the inner slug is the canonical model identifier.

How it works

Every task falls into one of three approaches:

ApproachWhenReturns
direct_llmTask needs only an LLM (code, writing, analysis)Best model + cost estimate
mcp_serverTask needs an external tool (search, email, calendar)Best tool + best model
multi_toolCompound task ("send Slack AND update Jira AND email")Ordered orchestration chain

Routing uses an LLM classifier (~$0.00001/call) for task understanding, then ranks candidates on a 5-dimension score:

Value Score = 0.35 × Output Quality            + 0.25 × Reliability            + 0.15 × Efficiency            + 0.15 × Cost            + 0.10 × Trust

Every reported outcome updates the scores. The routing gets more accurate as more agents use it.

Benchmark results

132 blind A/B executions across code, writing, analysis, structured output, and translation.

ToolRouteFixed GPT-4o
Quality wins60
Ties99
Losses0—
Avg cost$0.001–0.01$0.03–0.10

API

EndpointMethodDescription
/api/routePOSTRoute a task to best MCP server + LLM (unified)
/api/route/modelPOSTRoute to best LLM model only (no MCP server)
/api/mcpPOST (JSON-RPC)MCP server — 16 tools
/api/mcpGET (SSE)SSE transport for MCP clients
/api/reportPOSTReport MCP server outcome (lightweight)
/api/contributionsPOSTAdvanced MCP skill telemetry (requires skill_id or skill_slug in payload)
/api/report/modelPOSTReport LLM model outcome — use this for model telemetry, not /api/contributions
/api/verify/modelPOSTVerify model output quality
/api/skillsGETSearch MCP server catalog
/api/agents/registerPOSTRegister agent identity
/api/agents/preferencesPOSTSet routing preferences (Strategy D Phase 2 — allow_china, regulated_industries)
/api/healthGETService health check (DB + uptime)
/api/metricsGETPublic aggregate platform metrics (no auth)

Full reference at toolroute.io/api-docs

SDK

bash
npm install @toolroute/sdk
typescript
import { ToolRoute } from '@toolroute/sdk'
const tr = new ToolRoute()const rec = await tr.route({ task: 'parse this CSV and summarize it' })// execute with rec.recommended_model ...await tr.report({ skill: rec.recommended_skill, outcome: 'success', latency_ms: 1400 })

Self-hosting

bash
git clone https://github.com/grossiweb/ToolRoute.gitcd ToolRoutecp .env.local.example .env.localnpm installnpm run dev

Requires: NEXT_PUBLIC_SUPABASE_URL, NEXT_PUBLIC_SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY

How routing works

ToolRoute classifies each task using an LLM classifier (Gemini Flash Lite, ~$0.00001/call) with a keyword fallback. The resulting tier maps to a specific model via src/lib/routing/tiers.ts. Live pricing and capability data come from the models table. See docs/architecture.md for the full picture.

Stack

Next.js 14 (App Router) · Supabase (Postgres) · Vercel

License

MIT

Source: README.md at commit 40b88de

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts