Serper (Unofficial)
Server Details
Unofficial Serper MCP — wraps the Serper Google Search API (serper.dev)
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- pipeworx-io/mcp-serper
- GitHub Stars
- 0
- Server Listing
- mcp-serper
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 47 tools
The set contains several overlapping entry points that compete for the same routing/research job: ask_pipeworx, ask_pipeworx_beta (explicitly identical right now), ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions. Prediction-market and company-research tools also overlap heavily (bet_research vs polymarket_edges vs polymarket_arbitrage; company_facts vs entity_profile vs recent_changes vs compare_entities), creating real misselection risk despite detailed descriptions.
Names are consistently snake_case with no camelCase mixing, which is good. However, the convention itself is mixed: some are verb_noun (compare_entities, resolve_entity, validate_claim), many are noun-only (news, places, entity_profile, company_facts), and some are single verbs (search, remember, subscribe), so the pattern is readable but not predictable.
At 47 tools this is far above a well-scoped set and includes multiple near-duplicate meta/routing tools plus dense clusters of prediction-market and company-research tools. The server's broad gateway purpose may justify many capabilities, but the surface is too large and redundant for an agent to choose from reliably.
The surface covers a very broad range: web/news/places search, archives, company identifiers and financials, prediction markets, memory, subscriptions, AI visibility, dependency scanning, and document search. Minor gaps remain, such as no standalone fetch_url tool despite references to it, and some workflows are only reachable indirectly through ask_pipeworx/deep_research.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Unofficial SerpApi MCP — wraps SerpApi (serpapi.com) search engines
Unofficial Tavily MCP — wraps the Tavily API (tavily.com)
MCP server for Google search results via SERP API
Official SerpApi MCP server for Google, Bing, and other search engines.
Related MCP Servers
FlicenseNot gradedqualityCmaintenanceMCP server for the Serpent API — gives AI agents live Google, Bing, Yahoo, DuckDuckGo and Brave search results as structured JSON.-- FlicenseBqualityBmaintenanceEnables integration of Google search functionality into MCP-enabled applications using the Serper API, providing rich search results, configurable parameters, and efficient response handling.148-
- AlicenseNot gradedqualityDmaintenanceMCP server for using various search tools like Tavily API. Planning to support various search tools (i.e. wiki search, searxng, etc)3MIT

SerpBase MCPofficial
AlicenseNot gradedqualityDmaintenanceGoogle SERP API MCP server for AI agents. Gives Claude, Codex, Cursor, Cline and other MCP clients live Google Search, Images, News, Videos and Maps results as structured JSON through SerpBase.2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.