hyperroute-mcp
OfficialAllows routing to the Semantic Scholar Graph API via HyperRoute, enabling agents to search academic papers and citations and execute queries server-side after connecting a key.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@hyperroute-mcpFind the best tool for searching recent papers, connect my key, and run it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
hyperroute-mcp
The official Model Context Protocol server for HyperRoute.
HyperRoute is a router for AI agents. Give it a task and it picks the best external tool for that task — measured, not advertised — then runs the tool for you with your own key held server-side, and learns from how it went. This MCP server is how a coordinator agent (Claude Code, Codex, Goose, Cursor, LangGraph, …) drives it:
recommend → onboard a key → execute the tool server-side → report the outcome
It talks to the router only over its public HTTP API and holds no product logic of its own.
Why route at all
An agent with 100 tools bolted on has a context problem and a quality problem. HyperRoute
replaces both with one verb: your agent learns recommend, and HyperRoute decides which of
hundreds of tools actually answers this task, whether you can already do it better yourself,
and what it will cost.
Measured, not advertised. Every capability score is backed by real graded probes you can inspect (
describe(tool_id, ["evidence"])).Your keys never leave the server. You connect a key once; HyperRoute runs the tool with it and returns only the result. The key is never sent to your agent, never logged.
It tells you when NOT to route. If nothing beats what your coordinator already does, the verdict is
use_native— do it yourself. That only works if the server knows which coordinator it runs inside; see Declaring your coordinator.
Related MCP server: ToolRoute
Install
pip install hyperroute-mcpOr with pipx, so the command is always on your PATH regardless of which
virtualenv is active — which is what MCP clients need, since they launch the server themselves:
pipx install hyperroute-mcpFrom source, for development:
git clone https://github.com/HyperRouteAI/hyperroute-mcp
cd hyperroute-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e .Requires Python ≥ 3.10.
Add it to your coordinator
Claude Code
claude mcp add hyperroute -- hyperroute-mcpIf you installed into a virtualenv rather than with pipx, hyperroute-mcp is only on your PATH while
that venv is active — and MCP clients launch the server themselves, outside your shell. Give them the
absolute path in that case: /path/to/.venv/bin/hyperroute-mcp.
OpenCode — copy opencode.json into your project. OpenCode is bring-your-own-model,
so the server can't infer what you're running from the client name alone: set HYPERROUTE_COORDINATOR
(or HYPERROUTE_NATIVE_TOOLS) to match the model you actually point it at, or HyperRoute will have no
baseline for you. AGENTS.md carries the operating loop and the methodology — drop it in
so the agent can both act correctly and explain how the routing works.
Any MCP client (mcp.json / claude_desktop_config.json / equivalent):
{
"mcpServers": {
"hyperroute": {
"command": "hyperroute-mcp",
"env": { "HYPERROUTE_BASE_URL": "https://hyperroute.io" }
}
}
}Then just ask: "Use HyperRoute to find the best tool for searching recent papers, connect my
key, and run it." The agent calls recommend → connect_info → onboard → execute on its
own.
Authenticate once
recommend and browsing are public — no account. Connecting keys and running tools need one.
Preferred: mint a personal access token at hyperroute.io and hand it to
the use_token tool (or set HYPERROUTE_API_KEY). Your password never enters the conversation.
The token is then cached on disk (~/.hyperroute/token.json, mode 0600, keyed by router
URL), so every new MCP session restores your login silently. You are asked to authenticate again
only if the router invalidates the token. A full inline register → verify email-code flow is
also available for headless use.
Declaring your coordinator
HyperRoute compares external tools against what you can already do. That baseline is the set of coordinators that are free to you — and it is empty by default, because the router never assumes you have one. An MCP server that does not declare itself gets an external tool recommended for every task, including tasks the coordinator does better itself.
This server declares it for you. It reads the MCP client identity your coordinator sends on
connect and maps it to the coordinator HyperRoute models (claude-code → claude_code, …).
Check what it resolved with the session_info tool: if native_tools is empty, set it yourself.
"env": {
"HYPERROUTE_COORDINATOR": "claude_code", // or codex / cursor / goose / …; "none" disables
"HYPERROUTE_HELD": "anthropic_max_5x" // subscriptions you already pay for → priced at $0
}HYPERROUTE_NATIVE_TOOLS takes exact tool ids if you want to pin one model variant instead of the
whole product family.
Configuration
Variable | Default | Meaning |
|
| Which router to talk to. Override to point at a different instance. |
| — |
|
|
| Per-request timeout, seconds. |
|
| Where the cached login lives. |
| auto-detect | Which coordinator this runs inside; |
| — | Exact coordinator tool ids, overriding detection. |
| — | Comma-separated plan groups you hold, e.g. |
Tools
Tool | What it does |
| Base URL, login state, and the coordinator this server declares. Call first. |
| Router readiness + the loaded model bundle. |
| The main verb. Task → ranked tools as a compact table + how to act. Public. |
| Pull ONE tool's depth on demand: |
| Every facet a tool can be judged on, with defaults. Fetch once. |
| Your standing constraints, applied to every future route. |
| A tool's onboarding process: signup URL, steps, whether you're connected. |
| Save + test one tool API key under your account. Stored encrypted, reused forever. |
| Your connected tools (keys masked). |
| Run the chosen tool server-side with your held key; returns only the result. |
| Page through a result too large to inline. |
| Per-call feedback — the signal that sharpens future routing. |
| Open-ended feedback about a whole run. |
| Human-readable management view: history, tools, keys, stats. |
| Account lifecycle. |
| HyperFeed: curated agentic-AI news, agent releases, and SF events — plus your agent's personalized daily brief. |
The wire is deliberately lean
recommend answers with a compact table, not a catalog dump:
session: s-6d6c5a95f9f84d9a
verdict: interpose
refine: freshness, cited_references, source_quality
tool name price use why
→ opencitations OpenCitations Index free ready highest-ranked: capability 0.81 …
semantic_scholar Semantic Scholar Graph API free needs_key lower capability (0.75 vs 0.81).
confidence: med (on the pick)
act: execute('opencitations', <query>)Everything else — descriptions, per-plan pricing, per-facet breakdowns, the probe evidence behind
a score — is pulled for the one tool that matters via describe. That keeps a route roughly an
order of magnitude cheaper in tokens than shipping the full object on every call.
The use column is the whole auth story: ready (run it) · needs_key (connect first) ·
native (do it yourself) · soon (not runnable server-side yet).
Two-pass refinement
Pass 1 always returns a usable ranking. The refine: line names the unset preferences that would
reorder these candidates; fill the relevant ones and call recommend again with facets for a
personalized result. Durable constraints (GDPR, a budget cap) belong in set_preferences
instead — stored once, applied to every future route.
Development
pip install -e ".[dev]"
pytest
ruff check .The suite is fully offline — the router is faked, so no network and no real account are touched.
Set HYPERROUTE_BASE_URL to try it against a different router instance.
License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceMCP server for AgentPay — the payment gateway for autonomous AI agents. Fund a wallet once, give your agent the key, and it discovers, provisions, and pays for tool APIs on its own. One key, every tool.Last updated1121MIT
- Alicense-qualityAmaintenanceIntelligent routing layer for AI agents — recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.Last updated71MIT
- Alicense-qualityDmaintenanceA production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.Last updated54MIT
- Alicense-qualityAmaintenanceMCP server that enables AI agents to run a deterministic orchestration loop with decomposition, subagent execution, and review feedback across multiple LLM backends.Last updated53MIT
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
HiveCompute MCP Server — decentralized inference router for AI agents
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/HyperRouteAI/hyperroute-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server