# Agent Budget Router

> Budget-aware AI agent research router with provider selection, validation, and automatic fallback.

- name: io.github.kasp3965-bit/agent-budget-router
- version: 7.1.1
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 68/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.kasp3965-bit%2Fagent-budget-router
- tools: https://api.protogrid.dev/v1/servers/io.github.kasp3965-bit%2Fagent-budget-router/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-budget-router": {
      "type": "http",
      "url": "https://agent-budget-router-v7.movt1677.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-99% +updated-19d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 68/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: execute_task (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); optimize_task (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 174 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 174 tokens to load them all
- tool set hash: 36aca7b1110556d6db6b5b523e2ecac3
- tools last changed: 2026-10-01T04:36:21.566Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.kasp3965-bit/agent-budget-router.svg)](https://protogrid.dev/servers/io.github.kasp3965-bit/agent-budget-router)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-01 `execute_task` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Execute a research task using a free provider, validate the result, and automatically fall back to another free provider if needed.
  - after: Execute a research task using a validated provider. This tool costs $0.01 USDC per successful call.
- 2026-10-01 `optimize_task` changed (inputSchema, outputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.kasp3965-bit%2Fagent-budget-router/changes

## Remotes

- https://agent-budget-router-v7.movt1677.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.98734176)

## Packages

_none_

## Tools (2)

- `execute_task`: Execute a research task using a validated provider. This tool costs $0.01 USDC per successful call.
- `optimize_task`: Choose the best available free provider for an AI-agent research task based on task relevance and budget.