Skip to main content
Glama
kostyk348

sint-epistemic-mcp

by kostyk348

sint-epistemic-mcp

Epistemic Status Tracking MCP server — tracks what an agent KNOWS vs INFERS vs ASSUMES with calibrated confidence.

Tools

Tool

Description

epistemic_register(claim, status, confidence, source, domain)

Register a knowledge claim with epistemic status

epistemic_status(claim_query, domain)

Look up claims by text or domain

epistemic_calibrate(domain)

Get calibration accuracy stats for a domain

epistemic_gaps(domain)

Identify domains with high ASSUMED/UNCERTAIN ratio

epistemic_graph(domain)

Export knowledge status as a graph (nodes + edges)

epistemic_stats()

Summary statistics across all claims

Related MCP server: memorygraph

Status Types

  • VERIFIED — confirmed by external validation

  • INFERRED — logically derived from verified claims

  • ASSUMED — taken as true without verification

  • UNCERTAIN — insufficient evidence either way

Usage

Add to your MCP config:

{
  "mcpServers": {
    "sint-epistemic-mcp": {
      "command": "python",
      "args": ["/path/to/sint-epistemic-mcp/server.py"]
    }
  }
}

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Provides a compiled knowledge substrate, extracting atomic claims from an append-only capture log and querying a bitemporal claim graph over MCP. Read-only by default, with opt-in writes for trusted sources.
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.
    5
    Apache 2.0
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables agents to classify every claim into evidence tiers (FACT/INFERENCE/SPECULATION/UNVERIFIED) with attached evidence, forcing deterministic, evidence-gated reporting without LLM or network calls.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Belief-tracking memory for AI agents. Remember, recall, and ask why: every memory carries evidence, contradictions are surfaced, and retracted facts take their conclusions with them. Zero dependencies, local, MIT.
    MIT