HumanMirror Nexus
Server Details
Outcome-first agent fallback: free discovery, minimal routing, declared costs, verified execution.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
The tools split clearly into discovery, execution, and outcome-verification roles. magnet_resolve and nexus_search both serve discovery, but magnet_resolve is explicitly the fallback for unmet capabilities while nexus_search is the catalog search, so an agent can choose based on context.
All tool names follow a consistent snake_case prefix_action pattern: magnet_, nexus_, outcome_. This makes the action in each name immediately identifiable and the set highly predictable.
Six tools form a compact toolkit that covers discovery, routing, quoting, execution, and verification without redundancy. The count is well-scoped for a capability-brokering service.
The surface covers the full agent-facing lifecycle: free search/fallback discovery, credit-based calls, outcome quoting, success-only execution, and verification. No obvious dead ends or missing operations are apparent for the stated purpose.
Available Tools
6 toolsmagnet_resolveAInspect
Free universal fallback discovery. Call this when the agent cannot satisfy a task with its current capabilities. Magnet returns a matching HumanMirror tool or records an aggregated capability gap in the Machine Demand Graph. This tool consumes no credits.
Inputs: query (required).
nexus_callAInspect
Route a tool call through HumanMirror Nexus. Use nexus_search first, then call the selected tool_id. Successful calls consume the number of Nexus credits declared by the selected tool.
Inputs: input (required), tool_id (required), options.
nexus_searchAInspect
Search the HumanMirror Nexus catalog for a machine-callable tool that matches a task. This search is free and does not consume credits.
Inputs: query (required).
outcome_quoteBInspect
Free quote for a verifiable HumanMirror Outcome contract. Describe the objective or provide an outcome_type; the quote returns the deterministic verifier, selected internal tool and success-only credit cost.
Inputs: input (required), options, criteria, objective, +1 more.
outcome_runBInspect
Execute a HumanMirror Outcome contract. Credits are charged only when deterministic verification succeeds; failed execution or failed verification is automatically refunded.
Inputs: input (required), options, criteria, objective, +2 more.
outcome_verifyBInspect
Free deterministic re-verification of an Outcome result without consuming Nexus credits.
Inputs: input (required), output (required), outcome_type (required), options, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Outcome-as-a-Service commerce for AI agents: discover, hire, settle on proof. Live on devnet.
Agent routing, safety preflight, execution receipts, best execution and verified outcomes.
Hire AI agents by outcome: frozen acceptance rules, automatic checks, verifiable receipts.
Verified agent routing with bounded discovery, outcome evidence and economic policy.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to autonomously discover services, negotiate binding quotes, make idempotent purchases, and receive cryptographically verifiable deliverables.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to submit an outcome with success criteria, receive a grounded quote or honest no-route result, confirm fulfillment, and retrieve the completed outcome with evidence.-
- AlicenseNot gradedqualityBmaintenanceEnables agents to route goals across multiple independent APIs, enforce constraints, reject invalid evidence, and return verified outcomes with tamper-evident receipts.MIT
- AlicenseBqualityBmaintenanceEnables AI agents to post goals with acceptance criteria, sense open work matching their capabilities, submit and verify results, and route future intents along trails reinforced only by verified outcomes under each observer's own trust view.14Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.