Other · Local MCP server
Cognos Session Memory
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.base76-research-lab/cognos-session-memory- Version
- 0.1.0
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-03-03
- Updated
- 2026-03-03
- Publisher
- base76-research-lab (GitHub) · 3 servers with pages here
- Repository
- github.com/base76-research-lab/cognos-session-memory
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | cognos-session-memory-mcp | 0.1.0 | stdio |
How to connect Cognos Session Memory
Cognos Session Memory runs locally from a Python package published to PyPI: cognos-session-memory-mcp version 0.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx cognos-session-memory-mcp. It reads the environment variable COGNOS_TRACE_DB; set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"cognos-session-memory": {
"command": "uvx",
"args": [
"cognos-session-memory-mcp"
],
"env": {
"COGNOS_TRACE_DB": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from base76-research-lab (GitHub)
| Server | Runs |
|---|---|
| Conductor Graph MCPExposes a CognOS agent system as a machine-readable graph. Full system snapshot with one tool call. | Local · stdio |
| Token CompressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. | Local · stdio |
More other servers
| Server | Runs |
|---|---|
| CogmemaiMemory for any Ai: remembers across sessions, enforces your rules before actions, reviews the work. | Local · stdio, HTTP |
| CogniRepoFAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline. | Local · stdio |
| Cognitive Ai MemoryEbbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall. | Local · stdio |
| Cognitive Substrate28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools. | Local · stdio |
| CoingeckoCoinGecko MCP — wraps CoinGecko free API (no auth required) | Remote · HTTP |
| Coinmetrics MCPKeyless Coin Metrics community asset metrics. | Local · stdio |
| Coinopai MCPAuditable market intelligence with calibrated forecast ranges, anomaly review, outcome. | Local · stdio |
| Coinrule MCPTrade, monitor portfolios, and build Coinrule strategies by chat. | Remote · HTTP |