@putervision/agent-reasoning-mcpSAFE
🧭 Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@putervision/agent-reasoning-mcp) [](./CHANGELOG.md) [](https://github.com/putervision/agent-reasoning-mcp/actions/workflows/ci.yml) [](https://nodejs.org) [](https://opensource.org/licenses/MIT)
Strategic BDI Reasoning, Multi-Attribute Expected Utility Theory & Decision Intelligence for Autonomous AI Agents
@putervision/agent-reasoning-mcp is a formal Model Context Protocol (MCP) server that provides strategic belief-desire-intention (BDI) reasoning, hierarchical goal decomposition, multi-attribute expected utility calculation (\(E[U] = \sum wi ui\)), exponential belief decay, quantitative risk evaluation, and reactive replanning across multi-modal memory bridges.
🌐 Official Documentation: putervision.com • Interactive Web Docs
⚡ 15-Second Quick Start
# 1. Initialize reasoning database & seed default utility profiles npx @putervision/agent-reasoning-mcp init # 2. Run health diagnostics and Merkle audit checks npx @putervision/agent-reasoning-mcp doctor # 3. Inspect active goals, intentions, and belief states npx @putervision/agent-reasoning-mcp inspect
🛠️ 15 Core MCP Tools
BDI Strategic Deliberation (10 Tools)
8d777d81961bOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add agent-reasoning-mcp -- npx -y @putervision/[email protected]
Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
aggressive | read | High combat and threat engagement bias |
aggressive_scout | read | Updated profile description |
aggressive_warrior | read | High combat aggression |
balanced | read | Default balanced autonomous profile |
balanced_autonomous | read | Balanced risk-reward profile for unattended super-loop runs |
cautious | read | High defense and risk aversion bias |
cautious_scout | read | Defensive survival |
echo_tool | read | Echo tool |
test_tool | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (9)
apiKey: 'sk-1234567890abcdef12345',
.prettierignore
.windsurfrules
import { SpatialSlice } from '../../schema/types.js';import { runMigrations, DecisionEngine, StatePackBuilder, canonicalJsonStringify } from '../../dist/lib.js';} from '../../dist/lib.js';
import { canonicalJsonStringify } from '../../src/utils/canonical-json.js';import { StatePackBuilder, computePackHash, verifyPackHash } from '../../src/engine/state-pack.js';better-sqlite3, @eslint/js, @types/better-sqlite3, @types/node, @vitest/coverage-v8, eslint, prettier, tsup
Gates applied: no_behavioural_pass.
8d777d81961bfull audit observations/trust-audit/mcp-server/putervision__agent-reasoning-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 8d777d81961b | SAFE | B | 89 | first audit |
Questions
What is the @putervision/agent-reasoning-mcp MCP server?
🧭 Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.
What tools does @putervision/agent-reasoning-mcp expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @putervision/agent-reasoning-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does @putervision/agent-reasoning-mcp need?
It reads DISPATCH_TOKEN_TTL_MS, PENTAD_HMAC_SECRET and TYPESAFE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does @putervision/agent-reasoning-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @putervision/agent-reasoning-mcp at 0.4.1.
How current is this page?
The grade is for one exact copy of the source (8d777d81961b), read on 2026-10-11. The repository is watched and re-audited when it changes.