TraceLattice

An MCP server that gives AI agents structured sequential thinking. Thoughts live in a DAG, reasoning strategies are pluggable, and confidence scores get calibrated against actual outcomes.

Features

• 11 thought types: regular, hypothesis, verification, critique, synthesis, meta, tool_call, tool_observation, assumption, decomposition, backtrack
• DAG-based thought graph with 8 edge kinds (sequence, branch, merge, verifies, critiques, derives_from, tool_invocation, revises) and topological traversal
• Pluggable reasoning strategies. Sequential by default, or Tree-of-Thought with BFS/beam search and plateau detection
• Tool interleave: suspend a thinking chain, run a tool call, then resume where you left off
• Confidence calibration using Beta(2,2) priors, Brier score, and Expected Calibration Error (ECE)
• Branch compression: cold branches get rolled into summaries automatically, with a sliding-window dehydration policy
• Outcome recording for tool_call/tool_observation results with metadata
• Tool and skill recommendations with confidence scores, rationales, and automatic discovery
• Per-session isolation with TTL eviction and LRU caching
• Three transports: stdio (default), SSE (legacy), Streamable HTTP (production)
• Strict TypeScript, Valibot validation, 1913 tests, 18-service DI container

Install

Requires Node.js v22+.

npm install -g tracelattice

Configure your MCP client

The default transport is stdio. Add the server to your client:

Claude Code

User-scoped (~/.claude.json) or project-scoped (.mcp.json in project root):

{
  "mcpServers": {
    "tracelattice": {
      "command": "tracelattice"
    }
  }
}

Or via CLI:

claude mcp add tracelattice -- tracelattice

Codex CLI

User-scoped (~/.codex/config.toml) or project-scoped (.codex/config.toml):

[mcp_servers.tracelattice]
command = "tracelattice"

Or via CLI:

codex mcp add tracelattice -- tracelattice

OpenCode

Global (~/.config/opencode/opencode.json) or project-scoped (.opencode.json):

{
  "mcpServers": {
    "tracelattice": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tracelattice"
      ],
      "enabled": true,
      "environment": {
        "MAX_HISTORY_SIZE": "10000"
      }
    }
}

Configuration

Server

Feature flags

All flags default to false. Set to true or 1 to enable.

Transport

Skill discovery

Transports

Set TRANSPORT_TYPE to pick one:

Development

npm install
npm run dev          # MCP inspector
npm test             # 1913 tests (vitest)
npm run test:coverage # with coverage report
npm run type-check   # tsc --noEmit
npm run lint         # eslint
npm run build        # rslib + rsbuild

Architecture

src/
├── core/               # Domain logic
│   ├── graph/          # DAG edges: Edge, EdgeStore, GraphView
│   ├── evaluator/      # SignalComputer, Aggregator, PatternDetector, Calibrator
│   ├── compression/    # CompressionService, DehydrationPolicy, SummaryStore
│   ├── reasoning/      # OutcomeRecorder + strategies (Sequential, TreeOfThought)
│   └── tools/          # InMemorySuspensionStore (suspend/resume)
├── contracts/          # Shared interfaces (cross-module coupling point)
├── persistence/        # File, SQLite, Memory backends
├── transport/          # stdio, SSE, Streamable HTTP
├── di/                 # IoC container (18 services)
├── registry/           # Tool/Skill discovery with LRU cache
└── config/             # YAML + env var loading

License

MIT