SSearch
Server Details
Free web search for AI agents. No API key required. Hosted MCP in active development.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
The search family (search_documents, search_web, search_plan, search_sources) is reasonably differentiated by description, and retrieval tools have distinct roles. However, get_context vs get_document overlap on 'retrieve stored text,' and search_documents vs search_web could be confused without careful reading. forward_canary is clearly distinct but out of domain.
All tools follow a consistent verb_noun snake_case pattern (fetch_page, get_context, get_document, search_documents, search_plan, search_sources, search_web, forward_canary). No mixed conventions or casing anomalies.
Eight tools is a well-scoped count for a search/corpus server. The only drag is forward_canary, a dev-only transport probe that doesn't serve the core search purpose and slightly dilutes the set.
Covers the search lifecycle well: plan, sources, document/web search, page fetch, and two retrieval tools. Minor gap: descriptions mention promoting successful misses into the live index, but no explicit index/promote tool is exposed.
Available Tools
8 toolsfetch_pageCInspect
Fetch and extract readable page text; optionally fall back to Common Crawl.
Inputs: url (required), max_chars, archive_fallback.
forward_canaryAInspect
Dev-only transport proof. Forward a fake canary transiently and return only delivery status. Never use a real credential.
Inputs: canary (required).
get_contextBInspect
Retrieve only the stored passages in a search result that are relevant to the information you need.
Inputs: query (required), document_id (required), max_chars, max_passages.
get_documentBInspect
Retrieve the broader stored text for a known SSearch document ID.
Inputs: document_id (required), max_chars.
search_documentsAInspect
Search SSearch-owned stored full-text documents. Successful misses can be promoted into the live index.
Inputs: query (required), promote, max_results.
search_planCInspect
Show the normalized local search plan for a query.
Inputs: query (required).
search_sourcesAInspect
Describe the local SSearch corpus and search backends.
Inputs: no named parameters.
search_webCInspect
Search SSearch. Set wait_for_coverage to search owned documents and, only if needed, external discovery on a miss.
Inputs: query (required), fresh, max_results, wait_for_coverage.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Web search API and MCP server for developers building AI agents.
Web scraping, extraction and search for AI agents. Hosted MCP with workspace API keys.
Scrape, crawl and search the web for AI agents via MCP.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Related MCP Servers
- AlicenseAqualityDmaintenanceFree, unlimited web search MCP server powered by Google AI Mode (Gemini) without API key. Provides real-time search results for AI agents like Claude, Cursor, and Windsurf.2MIT
- AlicenseAqualityDmaintenanceMCP server for web search powered by Google AI Mode (Gemini). Enables any AI agent to search the web in real-time for free and without rate limits.2189MIT
- AlicenseAqualityCmaintenanceFree, open-source web search gateway and MCP server for LLMs, AI agents, and RAG. It provides no-key web, code, academic, and community search with deduplication, ranking fusion, and citation-ready results.32MIT
- AlicenseAqualityDmaintenanceEnables AI agents to perform multi-engine web search, fetch web pages, and extract clean Markdown content via MCP, with no API keys required.377 PyPI8MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.