Koskamo

Context Cloud MCP

Context Cloud is a persistent AI memory server designed for engineering teams, offering shared workspaces, typed knowledge chunks, and cross-tool support. It enables AI coding sessions to maintain structured memory that works across tools and teammates, featuring two-layer retrieval with LLM-based selection and hybrid vector/BM25/RRF fusion search. The system automatically deduplicates knowledge and handles supersession of evolving facts, with zero server-side LLM costs as extraction occurs on the client AI tool.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Context Cloud MCP logo, by Context CloudCommunity listingLegacy SSEOAuth sign-inEndpoint checked 2026-11-01Published by Context Cloud
MCP endpoint (Legacy SSE)
https://api.contextcloud.pro/mcp/protocol
Vendor documentation

What you can do with it

  • Commit structured knowledge from current AI sessions to shared team knowledge bases
  • Perform hybrid vector and BM25 semantic search across shared team knowledge bases
  • Check for changes to knowledge bases since the last session or specified date
  • List, create, rename, or archive knowledge bases within a workspace

Source and maintenance

Community listingRegistry 0.1.8
mcp-registry: io.github.abhinavala/context-cloud@0.1.8Source repositoryProject website
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
303 ms
95th percentile latency
303 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 303 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport sse context-cloud-mcp-contextcloud https://api.contextcloud.pro/mcp/protocol

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "context-cloud-mcp-contextcloud": {
      "type": "sse",
      "url": "https://api.contextcloud.pro/mcp/protocol",
      "disabled": false
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport sse context-cloud-mcp-contextcloud https://api.contextcloud.pro/mcp/protocol

Let your agent find its tools

Find servers like Context Cloud MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,641