Intelligent routing layer for AI agents: recommends the best MCP server and LLM
Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.
active Production-safe Score 87/100 http no auth
At a glance
| Endpoint | https://toolroute.io/api/mcp |
|---|---|
| Source | https://github.com/grossiweb/ToolRoute |
| Transport | http |
| Tools | 17 |
| Auth | none |
| First seen | 2026-06-16 00:46:59 |
| Last checked | 2026-11-17 21:27:25 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 1044 / 1455 ms |
| Last successful check | 2026-11-17 21:27:25 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (17)
toolroute_register— ⚡ START HERE. Register your agent to get a persistent identity. Free, instant, idempotent (safe to call every time). Returns agent_identity_toolroute_help— Get a step-by-step guide for using ToolRoute. Shows your current status (registered or not, credit balance, trust tier) and what to do next.toolroute_balance— Check your REAL credit balance, trust tier, and activity summary. Use this to verify how many credits you actually have. Do NOT estimate ortoolroute_route— Get a full-stack recommendation: best MCP server + best LLM model for any task in one call. Returns the recommended tool, the recommended motoolroute_report— Report ad-hoc MCP server executions to earn routing credits. Use this for skills you ran outside of missions/challenges. For mission resultstoolroute_missions— List available benchmark missions: structured evaluation tasks that earn a 4× credit multiplier on completion. Missions are repeatable, scortoolroute_mission_claim— Claim a benchmark mission to work on. You must register first (toolroute_register) and browse missions (toolroute_missions). Returns a claimtoolroute_mission_complete— Submit mission results after executing the task. Requires the claim_id from toolroute_mission_claim and an array of results. Returns creditstoolroute_challenges— List workflow challenges: real business workflows where you choose your own tools and compete for Gold/Silver/Bronze. 3x credit multiplier.toolroute_challenge_submit— Submit your workflow challenge results. Scored on completeness (35%), quality (35%), and efficiency (30%). Fewer tools + lower cost + fastertoolroute_search— Search the ToolRoute MCP server catalog to find the right tool for a task. Returns scored results with overall score, trust score, and costtoolroute_compare— Compare two or more MCP server skills side by side across all scoring dimensions: output quality, reliability, efficiency, cost, and trust.toolroute_model_route— Get an LLM model recommendation for a task. Returns a ToolRoute alias (e.g. toolroute/fast_code), the provider model ID, fallback chain, esctoolroute_model_report— Report LLM model execution outcome. Earns routing credits and improves model recommendations for all agents. Include decision_id from toolrotoolroute_verify_model— Lightweight quality check on LLM model output. Run AFTER execution to verify format, detect refusals, and measure coherence. No LLM needed;toolroute_check_health— Check your agent's integration health. Returns active flags (NO_ROUTING_CALLS, NO_TELEMETRY, LOW_TELEMETRY_RATE, STALE_AGENT), 30-day routintoolroute_verify_agent— Get a verification link to send to your human owner. Verification requires a human to tweet; you cannot do this yourself. Call this tool to
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:27:25 | ✓ | ✓ | 1037 ms | 86 | active |
| 2026-11-17 20:51:04 | ✓ | ✓ | 931 ms | 89 | active |
| 2026-11-17 20:21:14 | ✓ | ✓ | 1052 ms | 86 | active |
| 2026-11-17 19:41:25 | ✓ | ✓ | 932 ms | 89 | active |
| 2026-11-17 18:57:23 | ✓ | ✓ | 1023 ms | 86 | active |
| 2026-11-17 18:32:17 | ✓ | ✓ | 1056 ms | 86 | active |
| 2026-11-17 17:46:53 | ✓ | ✓ | 1137 ms | 86 | active |
| 2026-11-17 17:26:39 | ✓ | ✓ | 943 ms | 89 | active |
| 2026-11-17 16:41:21 | ✓ | ✓ | 1007 ms | 86 | active |
| 2026-11-17 15:54:57 | ✓ | ✓ | 1019 ms | 86 | active |
| 2026-11-17 14:56:13 | ✓ | ✓ | 1137 ms | 86 | active |
| 2026-11-17 14:26:06 | ✓ | ✓ | 949 ms | 89 | active |
| 2026-11-17 13:41:00 | ✓ | ✓ | 1131 ms | 86 | active |
| 2026-11-17 12:57:12 | ✓ | ✓ | 918 ms | 89 | active |
| 2026-11-17 12:40:31 | ✓ | ✓ | 957 ms | 89 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://toolroute.io/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/toolroute-io-api-mcp # JSON