
WebRouter
io.github.NimblewayPublished by GitHub account Nimblewayv0.13.0Updated Nov 16, 2026
Search, extract, answer, research and browse the web through one interface, across many providers
The publisher's own server: 370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation
Overview
WebRouter's local MCP server; no sign-in required; STDIO.
No AI overview yet: these facts come from the registry entry and the server itself.
Installation
In SourceWeft
- Open WebRouter in the dashboard and add it to a workspace.
- 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
WebRouter
The open source standard for agent web access.
One typed interface for search, extract, answer, research, live data and browsers, across two dozen providers.
[PyPI] [License: Apache 2.0] [Python 3.11 to 3.13] [CI] [Join WebRouter on Discord]
Documentation · Quickstart · Providers · Examples · Discord
Developer preview: the API may change before 1.0. Share feedback on Discord.
Every web API for agents has its own SDK, parameter names and response shape. WebRouter puts one interface in front of all of them, so switching provider is one argument, a failing provider falls back to the next, and your agent code never changes.
Why WebRouter
- One call shape, every provider. The same request and the same typed
response from Tavily, Exa, Brave, Perplexity, Firecrawl, Nimble and the rest.
Nothing is lost: unmapped fields stay in
extraand the raw payload inraw. - Never silently weaker. An option a provider cannot honour raises
UnsupportedParameterErrorinstead of being dropped, so a call never runs under looser constraints than you asked for. - Routing based on published benchmarks.
autotries the providers you hold keys for in the order committed benchmark results rank them, and falls back on an error or an empty answer.response.provideralways says who answered. - Cost control. Every response says what it cost and how long it took. Cap a call or a whole session in dollars and seconds, try the free backends first, and keep a log of what you spent (budgets).
- Keyless to start. Search, extract and a local browser work with no API key. Every key you add unlocks more providers and fallbacks.
- Built for agents. An MCP server, plus ready-made tools for LangChain, Claude and OpenAI agents.
- Measure, don't guess.
benchmark()andevaluate()compare providers on your own queries and score their accuracy against known answers. - Yours to run. Apache 2.0, runs in your process with your own keys, and sends each key only to its own provider.
Install
Python 3.11 or later. Extras per method (search, extract, research,
answer, browser, mcp, ...) keep the install small; see the
Quickstart.
Keys are read from the environment. Copy .env.example, which
names every variable and where to get it, and fill in the ones you hold.
Methods
Every method has an async twin on AsyncWebRouter.
Providers
Providers has each provider's key, the options it maps and how it was verified. Adding one is two methods: see Adding a provider.
Routing and fallback
For search, extract, answer, research and the browser methods, name no
provider and auto serves the call: every provider you hold a key for, in the
order committed benchmark results rank them,
then the free tiers. A member that fails, is rate-limited or answers empty
passes the call to the next. A member that cannot honour an option you set is
skipped for that call, and if none can, the call raises rather than running
without it. Live data has no fallback, since a source belongs to one vendor:
live_data_sources() with no provider searches every vendor you hold a key
for, and each source it returns names its own, which live_data() runs it on.
Vendor calls always name their vendor, since an account belongs to one.
A named provider is never quietly swapped for another: a missing key raises an
error naming the variable to set. In a service, share one router per process,
set timeout= on each call and turn on the web_router logger: see
Running in production. The auto order
lists each method's order and how it is generated.
Budgets and cost control
Every response carries cost_usd: the backend's own figure where it states
one (cost_source="reported"), else an estimate. Unless a router ranks the
backends itself (the default rules router does not), a cost cap makes auto
try the cheaper of the backends that score alike first.
Each attempt is checked against what is left before it starts, so parallel
calls never overspend together, and a backend that does not fit is skipped
with the reason recorded. Estimates come from the list prices shipped in
web_router.prices, not your bill. Only search (its keyless backends) and
open_browser (local) have a $0 backend; Cost and budgets
has the table per method, a fall-back for a batch that runs out, and the spend log. An
experimental router can also pick the method and provider for each prompt, and
url_policy="public_only" keeps a planned call off private and cloud-metadata
hosts. See Smart routing.
Use it from an agent
MCP server. Every method as a tool, running on your machine with your keys:
The MCP guide covers Claude Desktop, Cursor and other clients, credentials, tool costs and browser guards.
Agent frameworks. Ready-made web_search and web_extract tools, with a
compact rendering for the model and the full response kept for you:
web_router.integrations.anthropic and web_router.integrations.openai give
Claude and OpenAI agents the same tools as plain tool definitions. See
Agent integrations.
Compare providers on your own queries
benchmark_extract() does the same for extract, and evaluate() scores each
provider's accuracy on a question set with known answers (SimpleQA, FRAMES,
SealQA or your own CSV) with an LLM judge. See
Benchmarks and evaluation, and
benchmarks/ for the published runs behind the default order.
WebRouter or calling each provider directly
Documentation
Contributing
Contributions are welcome, and the most useful one is small: map one more of a provider's options, or add a provider.
CONTRIBUTING.md has the workflow and the provider checklist, STYLE_GUIDE.md the review standards, and AGENTS.md the rules for AI coding agents working on this repo.
Community
- Discord: questions in #help, and what you built in #showcase.
- GitHub Issues: bugs and gaps in a provider's support.
- GitHub Discussions: proposals and design ideas.
- SECURITY.md: vulnerabilities. Never in a public channel.
Useful? Star the repo so more agent developers can find it. ⭐
License
Apache License 2.0. The SimpleQA grader prompt vendored at
src/web_router/evals/prompts/ keeps its own MIT license, in
LICENSE-simple-evals beside it.
Source: README.md at commit 149a0d4
Tools
0Version history
1- v0.13.0LatestNov 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
Other Router integrations
370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation
ai.routerOfficial publisher
Remote AI gateway MCP server that lets an assistant call 100+ chat models, generate images, and convert text to speech through one 370.ai API key.

SolGuard Solana Token-2022 Scanner & Safe-Swap Router
Published by GitHub account Tradelord223
Audits Solana SPL and Token-2022 mints for honeypot risks and builds unsigned Jito-protected buy and safe-exit swap transactions.

AgentCoin router + escrow (Base Sepolia testnet)
Published by GitHub account stos-technologies
AgentCoin lets an assistant find agent services, route tasks to sellers, place orders with USDC escrow or direct payment, and verify delivery on the Base…
Conduit Router — Governed MCP Routing
org.aimlds
A remote MCP endpoint that routes chat completions to LLM providers with policy checks, spend caps, metering and verifiable audit receipts.

KRouter
Published by GitHub account 398894496-arch
Local Markdown memory for coding agents: recalls what was settled before, cites the page, and says when it does not know.