io.github.TadFuji/kirok-mcp
Kirok Memory
Is the Kirok Memory MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-01.
Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation
needs mcp<2 probed 2026-11-14 · unchanged since 2026-11-01
A plain install of the package stops at the import below. These tool definitions are from a second install with mcp<2, started in a container with the network off, on 2026-11-01.
MCP error -32000: Connection closed ModuleNotFoundError: No module named 'mcp.server.fastmcp'. This is mcp 2.x, where FastMCP was renamed to MCPServer (from mcp
- Run it
- uvx --with 'mcp<2' kirok-mcp@1.4.2 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- kirok_mcp 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/TadFuji/kirok-mcp
- Registry
- active, updated 2026-07-20 · registry entry
- Changes
- 2 recorded, reachable in 0 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| KIROK_recall | 259 | 10 % |
| KIROK_retain | 249 | 9 % |
| KIROK_reflect | 235 | 9 % |
| KIROK_smart_retain | 223 | 8 % |
| KIROK_set_bank_config | 180 | 7 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- Synapse Layer — Zero-Knowledge Memory io.github.SynapseLayer/synapse-secure-memory · install failed
- GhostQA io.github.SyncTekLLC/ghostqa · not found
- io.github.SystemCraftsman/strimzi-kafka-cli · crashed on start
- GuardRails-MCP io.github.TAM-DS/guardrails-mcp · alive
- io.github.TeleAI-UAGI/telemem · alive
- io.github.TeodorMCP/universal-connector-mcp · needs mcp<2
- Librarian io.github.Terobyte/librarian · crashed on start
- io.github.Texan-NXTassist/nr-mcp · needs mcp<2
Servers that mention memory.
- AgentPlaybooks ai.agentplaybooks/agentplaybooks · needs auth
- Ambix ai.ambix/ambix · needs auth
- Atlaso Memory ai.atlaso/mcp · needs auth
- ai.butlerbrain/mcp · needs auth
- Contexel ai.contexel/contexel · needs auth
- Daystruct ai.daystruct.api/daystruct · alive
- DoneThat ai.donethat/donethat · needs auth
- ai.dataecho/mcp · alive
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-01 08:19 | needs mcp<2 | 2.2 s | 19 | 4.7k | 2.6k |
| 2026-10-18 06:46 | install failed |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The package imports FastMCP from mcp.server.fastmcp. mcp 2.0, the Python SDK of 28 July 2026, renamed FastMCP to MCPServer, and the package asks for mcp with no upper bound, so a plain install (uvx, pip) gets mcp 2.x and the server stops at the import. Installed with mcp<2, it starts and lists its tools. The fix for the publisher: pin mcp<2 in the dependencies, for example mcp>=1.2,<2, and publish a new version, or move to MCPServer as the SDK's migration guide says. Until then, run it with uvx --with 'mcp<2'.
The cause and the fix, with the code before and after: ModuleNotFoundError: No module named 'mcp.server.fastmcp'