io.github.vishaltorc/subconscious-mcp
Subconscious
Is the Subconscious MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-03.
Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.
needs mcp<2 probed 2026-11-15 · unchanged since 2026-11-03
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 2026-11-03.
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' subconscious-mcp@0.2.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- subconscious-mcp 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/vishaltorc/subconscious-mcp
- Registry
- active, updated 2026-06-10 · registry entry
- Changes
- 3 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 |
|---|---|---|
| drift_report | 223 | 23 % |
| remember | 214 | 22 % |
| recall | 192 | 20 % |
| echo | 191 | 20 % |
| forget | 94 | 10 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- Coda io.github.vish288/mcp-coda · needs env
- GitLab io.github.vish288/mcp-gitlab · needs args
- io.github.vishalsachdev/canvas-mcp · needs env
- Munim io.github.vishalsg42/munim · needs args
- OpenReflex io.github.vishnu-77/openreflex · alive
- Code-Graph-RAG io.github.vitali87/code-graph-rag · needs env
- Cookidoo MCP io.github.vitaliemiron/cookidoo-mcp · alive
- AgentTrust io.github.vitaliiserbynassisterr/agenttrust · crashed on start
Servers that mention remember or semantic.
- Agentic News ai.agentic-news/mcp · needs auth
- Context Link ai.context-link/context-link · alive
- xmp4 — Semantic code knowledge for your stack ai.example4/xmp4 · alive
- FindIP ai.findip/patent-search · needs auth
- InfoLang Memory ai.infolang/mcp · no DNS
- Khwan ai.khwan/khwan-mcp · TLS error
- Maguyva ai.maguyva/maguyva · needs auth
- Picsha AI ai.picsha/picsha · needs auth
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-03 08:46 | needs mcp<2 | 2.8 s | 6 | 1.7k | 977 |
| 2026-10-27 07:02 | crashed on start | ||||
| 2026-10-20 06:50 | 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'