Works With Agents MCP
PYPI · WWA-MCP
14 MCP tools: facts, pitfalls, skills, handoff protocols, trust scores, identity verification.
Available components
Last scanned (3 hours ago)
Scores higher than 59% of PyPI servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 114 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2427 tokens (~110/item across 22 items; 22 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 2 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 1 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 31 Oct 26 +1
- Stability: 0.97 → pass security
- 30 Oct 26 +14
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.97 functional
- 28 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 27 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 26 Oct 26 −15
- Malware scan: pass → unverified ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/wwa-mcp@1.0.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
wwa_bid_get ~52
Get the full content of a specific bid by its ID. Returns complete bid text, metadata, and sections.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Bid ID (from wwa_bid_search or wwa_bid_list) |
No output schema declared.
No examples provided.
wwa_bid_index ~132
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.
| Name | Type | Req | Description |
|---|---|---|---|
| client | string | yes | Client or buyer name |
| content | string | yes | Full bid content (markdown or plain text) |
| date | string | – | Bid date (ISO 8601) |
| sections | array | – | Section titles for structured access |
| status | string | – | draft, submitted, won, or lost |
| title | string | yes | Bid/proposal title |
| value | number | – | Contract value in GBP |
No output schema declared.
No examples provided.
wwa_bid_list ~63
List all bids in the library with optional status or client filter.
| Name | Type | Req | Description |
|---|---|---|---|
| client | string | – | Filter by client name |
| limit | integer | – | Max results (default 20) |
| status | string | – | Filter: draft, submitted, won, lost |
No output schema declared.
No examples provided.
wwa_bid_search ~72
Semantic search across the bid content library. Finds relevant past bids by matching against stored content. Returns snippets with relevance scores.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results (default 10) |
| query | string | yes | What are you looking for? (e.g. 'social value methodology', 'pricing approach') |
No output schema declared.
No examples provided.
wwa_bidmate_score ~107
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.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | object | – | Bidder profile with sectors, budget range, locations |
| tender | object | yes | Tender data (from wwa_tender_search results) |
| use_ai | boolean | – | Use AI-powered analysis (requires inference API access for paid tier) |
No output schema declared.
No examples provided.
wwa_blueprint_search ~127
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.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter: protocols, compliance, deployment, security, economics, architecture |
| limit | integer | – | Max results (default 10, max 25) |
| query | string | yes | What specification are you looking for? (e.g. 'handoff', 'trust score', 'deployment') |
No output schema declared.
No examples provided.
wwa_blueprint_validate ~90
Validate an implementation against a blueprint specification. Check if your handoff, deployment manifest, or trust score implementation conforms to the spec.
| Name | Type | Req | Description |
|---|---|---|---|
| implementation | object | – | The implementation to validate |
| name | string | yes | Blueprint name (e.g. 'handoff', 'trust-score', 'identity') |
| schema_type | string | – | Type of validation: handoff, deployment, trust-score |
No output schema declared.
No examples provided.
wwa_compliance_check ~138
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.
| Name | Type | Req | Description |
|---|---|---|---|
| implementation | object | yes | Implementation config to validate (dict with field paths) |
| regulation | string | yes | Regulation name (e.g. 'NHS DTAC', 'FCA SMR', 'GDPR', 'SOC 2') |
| rules | array | yes | List of compliance rules to validate against |
No output schema declared.
No examples provided.
wwa_devloop_setup ~70
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
wwa_facts_list_categories ~34
List all available fact categories and their counts. Use this to discover what knowledge domains are available before querying specifics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
wwa_facts_query ~147
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.
| Name | Type | Req | Description |
|---|---|---|---|
| attribute | string | – | Property name (e.g. 'path', 'version', 'domain'). Omit to search all. |
| category | string | – | Fact category: env, preference, project, reference, user_fact, auth |
| entity | string | – | What the fact is about (e.g. 'python', 'spfx', 'works-with-agents'). Omit to search all. |
| limit | integer | – | Max results (default 20, max 100) |
No output schema declared.
No examples provided.
wwa_generate_key ~75
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.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | A label for this key (e.g. 'my-agent', 'ci-server') |
No output schema declared.
No examples provided.
wwa_handoff_create ~236
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.
| Name | Type | Req | Description |
|---|---|---|---|
| completed | array | yes | List of completed items (what's done) |
| context | object | – | Dict of key context values (project_root, versions, env vars) |
| decisions | array | – | List of design decisions made so far |
| pitfalls_hit | array | – | List of pitfalls/failures encountered so far |
| regulatory_compliance | boolean | – | Enable regulated variant with audit fields |
| remaining | array | yes | List of remaining items (what still needs doing) |
| sender_agent_id | string | yes | ID of the agent sending the handoff |
| sender_session_id | string | yes | Current session ID of the sender |
| task_id | string | yes | Unique task identifier (e.g. 'SP-42', 'build-dashboard') |
| to_agent | string | – | ID of the intended receiving agent (optional) |
No output schema declared.
No examples provided.
wwa_handoff_validate_schema ~67
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.
| Name | Type | Req | Description |
|---|---|---|---|
| handoff | object | yes | The handoff document to validate |
No output schema declared.
No examples provided.
wwa_handoff_verify ~63
Verify a handoff document before accepting it. Validates structure, required fields, and completeness. Catches incomplete transfers before work begins — preventing context loss between agents.
| Name | Type | Req | Description |
|---|---|---|---|
| handoff | object | yes | The handoff document (JSON/dict) to verify |
No output schema declared.
No examples provided.
wwa_identity_verify ~151
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.
| Name | Type | Req | Description |
|---|---|---|---|
| key_format | string | – | Public key encoding: 'hex' or 'base64' |
| message | string | yes | The message that was signed |
| public_key | string | yes | Ed25519 public key (hex or base64) |
| sig_format | string | – | Signature encoding: 'hex' or 'base64' |
| signature | string | yes | Ed25519 signature (hex or base64) |
No output schema declared.
No examples provided.
wwa_pitfalls_lookup ~133
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.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional skill category filter (e.g. 'devops', 'software-development') |
| limit | integer | – | Max results (default 10, max 25) |
| query | string | yes | What problem are you debugging? (e.g. 'pypi trusted publishing', 'spfx scss alias', 'npm 403') |
No output schema declared.
No examples provided.
wwa_skills_list_categories ~31
List all available skill categories and their counts. Maps to directories under ~/.hermes/skills/.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
wwa_skills_search ~115
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.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional category filter |
| limit | integer | – | Max results (default 15, max 30) |
| query | string | yes | What capability are you looking for? (e.g. 'deploy to cloud run', 'spfx build', 'python pypi release') |
No output schema declared.
No examples provided.
wwa_sla_validate ~191
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.
| Name | Type | Req | Description |
|---|---|---|---|
| accuracy | number | – | Task completion rate (0.0–1.0) |
| compliance_atp_level | integer | – | ATP level used (1, 2, or 3) |
| latency_p95_seconds | number | – | 95th percentile latency in seconds |
| latency_p99_seconds | number | – | 99th percentile latency in seconds (regulated tier) |
| recovery_rate | number | – | Recovery success rate (0.0–1.0) |
| tier | string | yes | SLA tier: 'best-effort', 'production', or 'regulated' |
| uptime | number | – | Heartbeat success rate (0.0–1.0) |
No output schema declared.
No examples provided.
wwa_tender_search ~154
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.
| Name | Type | Req | Description |
|---|---|---|---|
| include_contracts_finder | boolean | – | Include Contracts Finder results (lower-value contracts) |
| include_find_tender | boolean | – | Include Find a Tender results (above-threshold contracts) |
| limit | integer | – | Max results per source (default 20, max 100) |
| max_value | number | – | Maximum contract value in GBP |
| min_value | number | – | Minimum contract value in GBP |
| query | string | – | Free text search (e.g. 'IT services', 'construction', 'social care') |
No output schema declared.
No examples provided.
wwa_trust_score_calculate ~179
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.
| Name | Type | Req | Description |
|---|---|---|---|
| peer_rating | number | – | Average peer rating (1.0–5.0) |
| pitfalls_contributed | integer | – | Number of pitfalls contributed to registry |
| skills_published_reuse_avg | number | – | Average reuse score of published skills (0.0–5.0) |
| success_rate | number | yes | Task completion rate (0.0–1.0) |
| uptime_percentage | number | – | Heartbeat uptime ratio (0.0–1.0) |
No output schema declared.
No examples provided.
How do I install the Works With Agents MCP server?
Works With Agents MCP runs locally as a PyPI package, launched with uvx wwa-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · wwa-mcp
claude mcp add vystartasv-wwa-mcp -- uvx wwa-mcp
What is the Works With Agents MCP server?
Works With Agents MCP is listed in the public MCP registry as io.github.vystartasv/wwa-mcp. 14 MCP tools: facts, pitfalls, skills, handoff protocols, trust scores, identity verification. This page covers its PyPI package (wwa-mcp).
Is the Works With Agents MCP server safe to use?
Works With Agents MCP scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Works With Agents MCP server expose?
Works With Agents MCP exposes 22 tools: wwa_facts_query, wwa_facts_list_categories, wwa_pitfalls_lookup, wwa_skills_search, wwa_skills_list_categories, and 17 more. Their descriptions and schemas cost roughly 2,427 tokens of context every time the server is loaded.
Is the Works With Agents MCP server still maintained?
Works With Agents MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Works With Agents MCP server under?
Works With Agents MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.