ssearch MCP server

• Registry namecc.ssearch/searchverified in the MCP registry

The registry name sits under ssearch.cc. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-23
• Tools8
• Server calls itselfOpen Agent Search
• Server version0.2.0
• Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 326 ms.

• Its tools do every use case we checked: search indexed pages for documentation; return source links and snippets to an agent; find relevant pages for a question.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer309 ms
• Space in an agent's context≈ 717 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsC · 69 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 7 of 8
• Not saying whether it only reads or can destroy: 8 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_web

  Search SSearch. Set wait_for_coverage to search owned documents and, only if needed, external discovery on a miss.

• search_documents

  Search SSearch-owned stored full-text documents. Successful misses can be promoted into the live index.

• get_context

  Retrieve only the stored passages in a search result that are relevant to the information you need.

• get_document

  Retrieve the broader stored text for a known SSearch document ID.

• fetch_page

  Fetch and extract readable page text; optionally fall back to Common Crawl.

• search_plan

  Show the normalized local search plan for a query.

• search_sources

  Describe the local SSearch corpus and search backends.

• forward_canary

  Dev-only transport proof. Forward a fake canary transiently and return only delivery status. Never use a real credential.