Wever Labs Agentic Rails
@CodeWever
About Wever Labs Agentic Rails
Commercial trust rails for agent work: scoped work orders, rail execution, receipt verification, Trust Ledger records, and Agent Work History.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"wever-labs-agentic-rails": {
"url": "https://weverlabs.com/api/mcp",
"transport": "http"
}
}
}Tools
89Search 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.
Overview
What is Wever Labs Agentic Rails?
Wever Labs Agentic Rails provides MCP-accessible commercial trust rails for agent work. It allows agents and developers to inspect rails, create scoped work orders, execute bounded workflows, verify receipts, and review Trust Ledger / Agent Work History evidence.
How to use Wever Labs Agentic Rails?
Point an MCP client to the endpoint https://weverlabs.com/api/mcp. Use the work-order API at https://weverlabs.com/api/work-orders to create and manage work orders. Review trust evidence via the Trust Ledger summary and Agent Work History endpoints.
Key features of Wever Labs Agentic Rails
- Inspect commercial trust rails for agent work
- Create scoped work orders
- Execute bounded workflows
- Verify work receipts
- Review Trust Ledger and Agent Work History evidence
- Access live proof pack with non-sample records
Use cases of Wever Labs Agentic Rails
- Agents need to execute trusted workflows with audit trails
- Developers inspect rail configurations before agent execution
- Verification of receipts after work completion
- Review of agent work history for compliance or debugging
- Demonstration of live, non-sample trust records to investors
FAQ from Wever Labs Agentic Rails
What is the MCP endpoint?
The MCP endpoint is https://weverlabs.com/api/mcp.
How can I see the Trust Ledger summary?
Use the Trust Ledger summary URL: https://weverlabs.com/api/work-history/summary.
How do I view Agent Work History?
Call https://weverlabs.com/api/agent-work-history?agent_id=weverlabs-first-live-agent-001.
What does the proof pack contain?
The proof pack shows observed non-sample records produced by the live work-order loop, demonstrating work moving from order to rail run to receipt verification to Trust Ledger record to Agent Work History.
Where is the OpenAPI specification?
The OpenAPI specification is at https://weverlabs.com/openapi.json.
Frequently asked questions
What is the MCP endpoint?
The MCP endpoint is `https://weverlabs.com/api/mcp`.
How can I see the Trust Ledger summary?
Use the Trust Ledger summary URL: `https://weverlabs.com/api/work-history/summary`.
How do I view Agent Work History?
Call `https://weverlabs.com/api/agent-work-history?agent_id=weverlabs-first-live-agent-001`.
What does the proof pack contain?
The proof pack shows observed non-sample records produced by the live work-order loop, demonstrating work moving from order to rail run to receipt verification to Trust Ledger record to Agent Work History.
Where is the OpenAPI specification?
The OpenAPI specification is at `https://weverlabs.com/openapi.json`.
Basic information
More Reasoning MCP servers
NeoCoder: Neo4j-Guided AI Coding Workflow
angrysky56An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.
Part 1. Real-Time LangGraph Agent with MCP Tool Execution
junfanz1This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
n8n Workflow Builder MCP Server
makafeliAI assistant integration for n8n workflow automation through Model Context Protocol (MCP). Connect Claude Desktop, ChatGPT, and other AI assistants to n8n for natural language workflow management.
Code Reasoning MCP Server
mettamattA code reasoning MCP server, a fork of sequential-thinking
ArduPilot MCP Server Sandbox
hfujikawa77ArduPilotドローンをAIエージェントから操作するMCPサーバーです。
Comments