Query the shared agent knowledge base. Facts are structured environment truths — Python paths, project structures, preferences, deployment targets. Agents discover facts without re-asking users or searching blindly.

List all available fact categories and their counts. Use this to discover what knowledge domains are available before querying specifics.

Search known failure patterns and verified fixes. Each pitfall comes from real agent failures — not LLM hallucinations. Covers deployment, packaging, tooling, configuration. Before debugging something new, check here first — someone probably broke it already.

Search the agent skill library for reusable workflows. Each skill is a battle-tested procedure with exact commands, known pitfalls, and verification steps. Before tackling a new task, search here — the procedure might already exist.

List all available skill categories and their counts. Maps to directories under ~/.hermes/skills/.

Create a structured agent-to-agent task handoff. When one agent must transfer an in-progress task to another, this ensures complete context transfer — no data loss, no silent drops, full attribution chain. Implements the Works With Agents Handoff Protocol v1.0.0-draft.

Verify a handoff document before accepting it. Validates structure, required fields, and completeness. Catches incomplete transfers before work begins — preventing context loss between agents.

Full schema validation of a handoff document against the Handoff Protocol v1.0.0-draft. Stricter than verify — checks types, UUIDs, status values, and protocol compliance.

Search the Works With Agents blueprint registry. Blueprints are CC BY 4.0 reference specifications for AI agent infrastructure — handoff protocols, trust scoring, compliance frameworks, deployment manifests, agent OSI model. Free to use, adapt, and implement.

Validate an implementation against a blueprint specification. Check if your handoff, deployment manifest, or trust score implementation conforms to the spec.

Calculate an AI agent trust score using the Works With Agents Trust Score spec v1.0.0-draft. Weighs task success rate (30%), pitfall contributions (20%), skill quality/reuse (20%), peer rating (15%), and uptime (15%). Returns score, tier, autonomy level, and improvement recommendations.

Verify an agent's Ed25519 cryptographic signature. Proves that an agent with a given public key signed a specific message. Used for subagent output verification, capability attestation, and agent-to-agent authentication. Implements Works With Agents Identity Protocol v1.0.0-draft.

Validate agent fleet metrics against SLA tier thresholds. Checks whether your agent fleet meets service level guarantees for best-effort, production, or regulated tiers. Implements Works With Agents SLA Framework v1.0.0-draft.

Validate an agent implementation against a Compliance-as-Code ruleset. Regulation-agnostic validation engine — supply any ruleset (DTAC, FCA, GDS, GDPR, SOC2, ISO 27001) and your implementation config. Implements Works With Agents Compliance-as-Code spec v1.0.0-draft.

Get the full Works With Agents SPFx Component Scaffolding (Dev-Loop) setup guide. Returns MCP server install instructions (pip install wwa-scaffold-mcp), available tools, dashboard features, and architecture. Agents discovering WWA infrastructure call this to learn about the scaffolding tool.

Generate a new API key for accessing Works With Agents MCP tools. No authentication required — returns a key with 'free' tier. Use the returned key in subsequent calls via the 'x-api-key' argument.

Search UK public-sector tender opportunities from Contracts Finder and Find a Tender. Returns combined, deduplicated results from both sources. Filter by keyword, value range, and status.

Index a past bid or proposal into the bid content library. Stores content locally with full-text search. Use this to build a library of past responses for future drafting.

Semantic search across the bid content library. Finds relevant past bids by matching against stored content. Returns snippets with relevance scores.

List all bids in the library with optional status or client filter.

Get the full content of a specific bid by its ID. Returns complete bid text, metadata, and sections.

Go/no-go scoring for a tender opportunity. Evaluates a tender against your bidder profile and returns a score (0-100), verdict, risks, and strengths. Can use AI analysis if API key provided.