Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
set_goalRegister, update, decompose, or manage hierarchical goals and task DAGs in the reasoning engine.Register, update, decompose, or manage hierarchical goals and task DAGs in the reasoning engine.
No input schema was published for this tool.
evaluate_situationIngest multi-modal situation snapshot, compute expected utilities against active weights, and output prioritized action recommendations.Ingest multi-modal situation snapshot, compute expected utilities against active weights, and output prioritized action recommendations.
No input schema was published for this tool.
replanRegenerate sub-task DAG and abort/recreate intentions upon unexpected blockers or environmental state changes.Regenerate sub-task DAG and abort/recreate intentions upon unexpected blockers or environmental state changes.
No input schema was published for this tool.
assess_riskCompute quantitative risk and threat assessment for candidate actions or plans against active utility weights.Compute quantitative risk and threat assessment for candidate actions or plans against active utility weights.
No input schema was published for this tool.
query_knowledgeSearch learned heuristic patterns, tactics, and past decision traces by context similarity.Search learned heuristic patterns, tactics, and past decision traces by context similarity.
No input schema was published for this tool.
set_utility_weightsConfigure and activate multi-attribute utility weights (aggression, caution, greed, exploration, cooperation).Configure and activate multi-attribute utility weights (aggression, caution, greed, exploration, cooperation).
No input schema was published for this tool.
get_decision_traceRetrieve explainable step-by-step chain-of-thought rationale, candidate utilities, and risk assessment for past decisions.Retrieve explainable step-by-step chain-of-thought rationale, candidate utilities, and risk assessment for past decisions.
No input schema was published for this tool.
manage_beliefsMaintain structured belief state with TTL expiration sweeps, exponential confidence decay, and category filtering.Maintain structured belief state with TTL expiration sweeps, exponential confidence decay, and category filtering.
No input schema was published for this tool.
manage_intentionsQueue, dispatch, track, and resolve behavior directives (wire contract) for behavior-mcp.Queue, dispatch, track, and resolve behavior directives (wire contract) for behavior-mcp.
No input schema was published for this tool.
manage_reasoning_dbDatabase maintenance, stats, SHA-256 Merkle audit verification, checkpoints save/restore, and diffs.Database maintenance, stats, SHA-256 Merkle audit verification, checkpoints save/restore, and diffs.
No input schema was published for this tool.
aggressiveHigh combat and threat engagement biasHigh combat and threat engagement bias
No input schema was published for this tool.
cautiousHigh defense and risk aversion biasHigh defense and risk aversion bias
No input schema was published for this tool.
balancedDefault balanced autonomous profileDefault balanced autonomous profile
No input schema was published for this tool.
13 of 13 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
76 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+64 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.