Orchestrates multi-step tasks across Atlassian services by routing to specialized MCP servers within its catalog.
Handles email operations by identifying and routing tasks to Gmail-integrated MCP servers as part of complex orchestration chains.
Selects and routes tasks to Google's AI models, optimizing for performance and cost across different task tiers.
Automates Jira issue management and updates by routing tasks to the appropriate Jira MCP server.
Integrates Meta's language models into task routing workflows for efficient code and chat generation.
Routes requests to OpenAI models, utilizing intelligent classification to pick the best model for quality and value.
Routes communication tasks to Slack MCP servers to enable automated messaging within agent workflows.
Routing layer for AI agents. One call returns the best MCP server and LLM for any task — scored on 132 real benchmark executions.
Add to any MCP client (Claude Code, Cursor, Windsurf, Cline):
{
"mcpServers": {
"toolroute": {
"url": "https://toolroute.io/api/mcp"
}
}
}Or via HTTP:
curl -X POST https://toolroute.io/api/route \
-H "Content-Type: application/json" \
-d '{"task": "search the web for recent AI papers"}'{
"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_modelis always an object, not a bare string — the innerslugis the canonical model identifier.
Related MCP server: Playwright MCP Server
Every task falls into one of three approaches:
Approach | When | Returns |
| Task needs only an LLM (code, writing, analysis) | Best model + cost estimate |
| Task needs an external tool (search, email, calendar) | Best tool + best model |
| Compound 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 × TrustEvery reported outcome updates the scores. The routing gets more accurate as more agents use it.
132 blind A/B executions across code, writing, analysis, structured output, and translation.
ToolRoute | Fixed GPT-4o | |
Quality wins | 6 | 0 |
Ties | 9 | 9 |
Losses | 0 | — |
Avg cost | $0.001–0.01 | $0.03–0.10 |
Endpoint | Method | Description |
| POST | Route a task to best MCP server + LLM (unified) |
| POST | Route to best LLM model only (no MCP server) |
| POST (JSON-RPC) | MCP server — 16 tools |
| GET (SSE) | SSE transport for MCP clients |
| POST | Report MCP server outcome (lightweight) |
| POST | Advanced MCP skill telemetry (requires |
| POST | Report LLM model outcome — use this for model telemetry, not |
| POST | Verify model output quality |
| GET | Search MCP server catalog |
| POST | Register agent identity |
| POST | Set routing preferences (Strategy D Phase 2 — |
| GET | Service health check (DB + uptime) |
| GET | Public aggregate platform metrics (no auth) |
Full reference at toolroute.io/api-docs
npm install @toolroute/sdkimport { 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 })git clone https://github.com/grossiweb/ToolRoute.git
cd ToolRoute
cp .env.local.example .env.local
npm install
npm run devRequires: NEXT_PUBLIC_SUPABASE_URL, NEXT_PUBLIC_SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY
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.
Next.js 14 (App Router) · Supabase (Postgres) · Vercel
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
HiveCompute MCP Server — decentralized inference router for AI agents
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/grossiweb/ToolRoute'
If you have feedback or need assistance with the MCP directory API, please join our Discord server