io.contextstream/mcp
ContextStream
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
timeout probed 2026-10-14
fetch failed | Connect Timeout Error (attempted address: mcp.contextstream.io:443, timeout: 10000ms) | UND_ERR_CONNECT_TIMEOUT
- Endpoint
- https://mcp.contextstream.io/mcp?default_context_mode=fast&src=registry (streamable-http)
- Host
- mcp.contextstream.io
- Repository
- https://github.com/contextstream/mcp-server
- Website
- https://contextstream.io/docs/mcp
- Registry
- active, updated 2026-07-13 · registry entry
- Reachable
- 5 of the last 6 probes
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 14:10 | needs auth | ||||
| 2026-10-05 00:27 | server error | ||||
| 2026-10-04 10:01 | needs auth | ||||
| 2026-10-04 07:54 | needs auth | ||||
| 2026-10-03 20:34 | needs auth | ||||
| 2026-10-03 17:51 | needs auth |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.contextstream/mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.