# @putervision/agent-reasoning-mcp

Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.1.2
- **Author:** PuterVision
- **License:** MIT
- **npm:** @putervision/agent-reasoning-mcp
- **Source:** https://github.com/putervision/agent-reasoning-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-12T17:06:21.088Z
- **Version scanned:** 0.1.2
- **CVEs:** none found by OSV at scan time

## Tools

13 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `set_goal` — Register, update, decompose, or manage hierarchical goals and task DAGs in the reasoning engine.
- `evaluate_situation` — Ingest multi-modal situation snapshot, compute expected utilities against active weights, and output prioritized action recommendations.
- `replan` — Regenerate sub-task DAG and abort/recreate intentions upon unexpected blockers or environmental state changes.
- `assess_risk` — Compute quantitative risk and threat assessment for candidate actions or plans against active utility weights.
- `query_knowledge` — Search learned heuristic patterns, tactics, and past decision traces by context similarity.
- `set_utility_weights` — Configure and activate multi-attribute utility weights (aggression, caution, greed, exploration, cooperation).
- `get_decision_trace` — Retrieve explainable step-by-step chain-of-thought rationale, candidate utilities, and risk assessment for past decisions.
- `manage_beliefs` — Maintain structured belief state with TTL expiration sweeps, exponential confidence decay, and category filtering.
- `manage_intentions` — Queue, dispatch, track, and resolve behavior directives (wire contract) for behavior-mcp.
- `manage_reasoning_db` — Database maintenance, stats, SHA-256 Merkle audit verification, checkpoints save/restore, and diffs.
- `aggressive` — High combat and threat engagement bias
- `cautious` — High defense and risk aversion bias
- `balanced` — Default balanced autonomous profile

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"agent-reasoning\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@putervision/agent-reasoning-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40putervision%2Fagent-reasoning-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40putervision%2Fagent-reasoning-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40putervision%2Fagent-reasoning-mcp
- HTML page: https://forgeregistry.com/registry/%40putervision%2Fagent-reasoning-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.