Loading…
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 26 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The wever-labs-service-resolver MCP server exposes 89 tools, focused primarily on filesystem and developer capabilities. Its published description reads: "Agentic rails for complex workflows with receipts, fees, and MCP tool access". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates wever-labs-service-resolver D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check wever-labs-service-resolver's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add wever-labs-service-resolver to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://weverlabs.com/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search Wever Labs first-party services and the official MCP Registry by capability. Discovery does not authorize execution.
Evaluate a service candidate against the Resolver v1 HTTPS, free, public-data, and read-only boundary.
Return ALLOW, REQUIRE_HUMAN, or DENY for a service under the Resolver v1 standing rules.
Use an allowed first-party read-only adapter, return the result, and record an honest signed or explicitly unsigned receipt state.
Return active rail contracts and movement fee schedule.
Return all active rails and required fields.
Return zero tool access cost and movement fee policy.
Return transaction and escrow movement fee schedule.
Return fee for a movement amount and type.
Return tool_access_units, movement_fee_units, total_units, currency, and return fields.
Return the Wever Labs Delegated Authority contract, supported tools, identity providers, rails, and enforcement boundary.
Validate a non-authoritative mandate draft for an exact principal, agent, scope, time window, and budget.
Return the verified mandate and durable lifecycle state for the credential-bound agent or authorized operator.
Check an exact action against a signed mandate, current lifecycle, and any required single-use action grant without executing it.
Execute a credential-bound write only after validating the signed mandate and a short-lived single-use action grant.
Evaluate an agent return package and return five scores, a continuation decision, a signed Agent Commerce Passport, and receipt verification.
Return only credential-bound, receipt-verified Commerce Proof missions that explicitly opted into public publication.
Evaluate a credential-bound agent return package, persist the proof record, and publish it when all verification requirements pass.
Return the machine contract for agent discovery, quote, payment, run, return package, and receipt proof.
Quote a rail and return payment options for autonomous agent completion.
Complete a rail run when a payment reference or verified checkout reference is present.
Complete paid run, build callback envelope, optionally deliver callback_url, and store callback proof.
Return payment-required object for rail movement.
Start a rail run with idempotency and payment reference.
Return run state.
Return package contract and hash.
Bind receipt to run and package.
Verify receipt hash and signature linkage.
Execute proof run through quote, package, receipt, and verification.
Run one rail through MCP proof path.
Read the approved external market source, compare the prior Atlas snapshot, persist a signed result, and route material changes for review.
Run active rails and return one release report.
Run external MCP client path and return transcript_hash.
Return client manifest and smoke sequence.
Issue scoped credential envelope.
Accept or reject scoped write.
Run one allowed action and one denied action to prove scoped boundaries.
Validate credential before returning a write envelope.
Sign receipt with managed signing metadata.
Verify versioned receipt signature.
Return new active signing version.
Verify receipt signature by declared signing_version.
Build callback packet.
Store callback, receipt, verification, and transcript references.
Return recent callback and receipt records.
Build directory and registry objects.
Return target-specific directory adapter payload.
Create target-specific directory submission record.
Return target-specific discovery payload.
Run active rails across multiple agent roles.
Return Supabase env and required table manifest.
Attempt to write test record to Supabase.
Store release report and transcript hashes.
Return stored or sandbox regression history.
Return persistent table manifest, RLS policy names, and schema cache reload instruction.
Persist multi-agent benchmark record as a release gate.
Persist issued credential fingerprint, scopes, allowed rails, and expiration.
Persist receipt, movement fee, verification, callback, and transcript references.
Return recent receipt ledger entries.
Return external client files and pass markers.
Run an external-style client path and return transcript_hash.
Return target-specific credential readiness without exposing credentials.
Return target surfaces, required files, verification checks, and cadence.
Return zero-cost tools and movement fee trigger.
Write and read every durable table as release proof.
Return recent live Supabase verification records.
Create target-specific registry submission and directory status records.
Return registry-grade MCP package metadata and public files.
Validate and optionally persist the hardened A2A Agent Card.
Return optional HTTP 402/x402-compatible payment challenge envelope with payment_reference fallback.
Return GitHub-ready external client repo package and smoke tests.
Persist target, credential state, submission hash, external status, and verification URL.
Return recent directory status records.
Check target credential environment and create credential activation records.
Fetch descriptor and listing URLs, then persist verification status.
Bind submission hash, verification URL, and status to a signed directory receipt.
Bind x402 challenge metadata to facilitator readiness or sandbox settlement state.
Create, update, complete, or read A2A task lifecycle records.
Return GitHub Actions smoke workflow and persist CI badge status.
Evaluate benchmark, Supabase, receipt ledger, directory, Stripe, and boundary checks.
Create Stripe Checkout Session for movement fee collection, or return env setup requirements.
Read Checkout Session status and persist payment state.
Return recent Stripe movement fee payment event records.
Use Claude inside Compliance EvidenceOps to analyze structured evidence packet context and return Wever Labs proof.
Bind Evidence Analysis output into Receipt Passport, Agent Run Ledger, Proof Relay, and Retry Manager state.
Run the investor proof arc: free proof signal, evidence analysis, verified receipt, ledger entry, and proof relay routing.
Complete a paid rail run from checkout session or payment reference, then return Receipt Passport, ledger entry, and Proof Relay state.
Record receipt, relay, payment-reference, and proof activity as usage and ledger-compatible events.
Validate rail, idempotency, and target surface.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: complete_paid_rail_run_with_callback
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "callback_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: store_regression_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "regression_report_id"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: execute_external_registry_submission_run
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "target_endpoint"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: update_directory_status_record
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "verification_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: verify_live_registry_listing
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "listing_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: sign_directory_submission_receipt
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "verification_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: run_durable_usage_ledger_event
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "next_endpoint"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
Use find_services, inspect_service, request_service_use, and run_RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.