A
licenseNot graded
qualityC
maintenanceEnables LLM agents to search the web and fetch pages as clean, budget-controlled text through MCP tools.
8
MIT
Spend Brake
by KIvanow
Related Servers
Alternatives to Spend Brake
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables free-first English and Chinese web search through zero-key engines plus optional paid providers, returning compact multi-source evidence with bounded token and request budgets. Each result exposes provenance, independent source counts, routing decisions, and visible provider failures so agents can verify claims rather than receive unexplained empty results.178 npmApache 2.0
- AlicenseAqualityCmaintenancePaid web research MCP tools for autonomous agents: search, page extraction, citations, and diff monitoring through a live x402 API. Unpaid calls return the Base USDC payment requirement so agents can pay and retry safely.41MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to run neural web searches, gather token-budgeted code context and documentation excerpts, and crawl individual pages through the Exa API.300 npmMIT
- AlicenseNot gradedqualityDmaintenanceWeb search for AI agents. Up to 10 results for $0.001 USDC via x402 on Base. No API key.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to run English and Chinese web searches without an API key, combining zero-key engines with optional paid providers and returning compact, provenance-tagged evidence under request and token budgets. Provider failures stay visible instead of being silently dropped, and additional tools extract URLs, GitHub READMEs, and Chinese technical articles.178 npmApache 2.0
TDQS
A3.6/5.0
Scored across 3 tools
Disambiguation4/5
brake_budget is clearly a read-only budget inspection tool, distinct from the two search tools. tavily_search and exa_search serve the same purpose (web search) and differ only by provider, which the descriptions make explicit, but an agent has no strong basis to choose between them besides name recognition.
Naming Consistency4/5
All names are snake_case and the two search tools follow a clean <provider>_search pattern. brake_budget breaks the action-first convention but is still readable and clearly grouped under the server's 'brake' concept.
Tool Count3/5
Three tools is thin for a spend-control server; the surface is essentially one read-only status tool plus two interchangeable search backends. It is not wrong for the purpose, but each tool barely stakes out distinct territory.
Completeness3/5
There is no way to set, raise, or reset caps, nor to view spend history or usage over time, so the budget lifecycle is read-only by design and leaves dead ends. Coverage of search is also limited to two providers with no fallback or aggregate search option.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues