recallradar-mcp

endpoint

https://www.nanoempireai.com/api/mcp

door code

602fcfef29097079

protocol

streamable-http ·2024-11-05

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is recallradar-mcp live?

Yes — it answered the hub's last check (checked 1h ago). It answered 99% of checks over the last 30 days.

Is recallradar-mcp free to use?

Yes — the hub reached it with no key and no payment.

What tools does recallradar-mcp have?

6 tools: astryx_compose_proof_ui, recallradar_check_product, recallradar_audit_manifest_info, skillproof_verify_repo, bidshield_triage_info, bidshield_evaluate_solicitation_gate.

Is recallradar-mcp safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• astryx_compose_proof_ui unknown never probed

  SUPPORTS: Deterministic composition of constraint-governed React 19 Proof-Native UI fragments (TrustManifestCard, SettlementReceipt, ComplianceMatrix, RecallDeltaTable) bound to trust-adaptive theme tokens (sovereign / sandbox / quarantine). DIFFERS FROM BASELINE: Unlike unconstrained generative UI prompts that hallucinate tailwind classes or omit cryptographic fields, Astryx enforces explicit visual invariants for machine-economy proofs. EXCLUDES: Does not execute arbitrary client-side scripts or unverified third-party component fetches.

  mcp-tool

  123456789101112131415161718192021222324252627

  {
    "type": "object",
    "required": [
      "component"
    ],
    "properties": {
      "component": {
        "enum": [
          "TrustManifestCard",
          "SettlementReceipt",
          "ComplianceMatrix",
          "RecallDeltaTable"
        ],
        "type": "string",
        "description": "Which Proof-Native Machine-Economy component to compose"
      },
      "trust_state": {
        "enum": [
          "sovereign",
          "sandbox",
          "quarantine"
        ],
        "type": "string",
        "description": "Optional trust-adaptive theme state override"
      }
    }
  }

  arguments 27 lines copy
• recallradar_check_product unknown 1h ago

  SUPPORTS: Deterministic sub-second consumer product screening (by name, brand, or UPC/GTIN) against 46,642 normalized North American (CPSC, FDA & Health Canada) recall records plus CPSC Unilateral Safety Warnings (including manufacturer-refused recalls like the 393,000 Tristar pressure cookers). DIFFERS FROM BASELINE: Unlike generic keyword web-scrapers or RAG chatbots that hallucinate recall statuses, RecallRadar executes exact entity resolution against a hash-locked 46,642-record corpus. EXCLUDES: Does not issue statutory legal warranties, formal Certificates of Compliance, or physical lab testing certifications.

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "required": [
      "name"
    ],
    "properties": {
      "upc": {
        "type": "string",
        "description": "Optional UPC / GTIN / EAN barcode"
      },
      "name": {
        "type": "string",
        "description": "Product title or model name"
      },
      "brand": {
        "type": "string",
        "description": "Manufacturer or brand name"
      }
    }
  }

  arguments 20 lines copy
• recallradar_audit_manifest_info unknown never probed

  SUPPORTS: Pricing and endpoint discovery for full wholesale/liquidation manifest audits ( USD Signed Recall Match Report, /mo RecallGuard Shield, ,400/yr Enterprise Data License, and x402 Base USDC endpoints) with 15 U.S.C. 2068 supplier-reimbursement evidence packets. DIFFERS FROM BASELINE: Unlike opaque enterprise quote forms, returns deterministic micro_usd pricing and instant Stripe/x402 settlement URLs. EXCLUDES: Does not execute a paid credit card charge without explicit human or x402 signature.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• skillproof_verify_repo unknown never probed

  SUPPORTS: Sub-200ms pre-execution verification of MCP servers and AI agent GitHub repositories across 28 pre-audited flagship repos, returning skillproof_score (0-100), commit tree_sha, line-cited code surface findings, delegation recommendation (ALLOW_BOUNDED / CONDITIONAL_SANDBOX_ONLY / HALT_HIGH_RISK), and RFC 8785 JCS Ed25519 Trust Manifest verification metadata. DIFFERS FROM BASELINE: Unlike post-hoc observability loggers that only record failures after treasury drain or policy breach, SkillProof intercepts delegation before execution and prevents upstream shortcut contamination (Stanford Collaborative Intelligence hand-off decay). EXCLUDES: Does not modify underlying agent model weights or take custody of external private keys.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "repo"
    ],
    "properties": {
      "repo": {
        "type": "string",
        "description": "GitHub full name in owner/repo format (e.g. pydantic/pydantic-ai)"
      }
    }
  }

  arguments 12 lines copy
• bidshield_triage_info unknown never probed

  SUPPORTS: Pre-bid compliance triage discovery across 882 live federal solicitations (CanadaBuys, SAM.gov) and locked human-verified audit tiers ( USD Pilot, USD Standard 19-Column Matrix, USD Full Proposal Suite). DIFFERS FROM BASELINE: Unlike generic proposal-writing bots that generate unverified prose, BidShield focuses strictly on fatal disqualifier detection before bid preparation spend. EXCLUDES: Does not submit government bids autonomously or replace licensed legal counsel.

  mcp-tool

  123456789

  {
    "type": "object",
    "properties": {
      "naics_code": {
        "type": "string",
        "description": "Optional 6-digit NAICS industry code (e.g. 238220 for HVAC)"
      }
    }
  }

  arguments 9 lines copy
• bidshield_evaluate_solicitation_gate unknown never probed

  SUPPORTS: Automated pre-bid and pre-action deontic compliance gate for federal solicitations and AP2 Human-Not-Present / AP4M mandates, evaluating solicitation text across 5 fatal disqualifier gates with sentence-bounded negation filtering and returning PASS_PRELIMINARY, CONDITIONAL_HUMAN_REVIEW, or HALT_FATAL_DISQUALIFIER plus quantified Decision Exposure (JEV) and Ed25519-signed REA commitment hashes. DIFFERS FROM BASELINE: Unlike flat-chunk RAG summarizers that miss negated clauses or treat outdated base-RFP clauses and newer Addenda as equal, BidShield applies deterministic deontic rules and emits an Ed25519-signed receipt. EXCLUDES: Does not write unverified creative fluff, submit final bids without human fiduciary sign-off, or replace licensed legal counsel.

  mcp-tool

  12345678910111213141516

  {
    "type": "object",
    "required": [
      "solicitation_text"
    ],
    "properties": {
      "naics_code": {
        "type": "string",
        "description": "Optional 6-digit NAICS code (e.g. 238220)"
      },
      "solicitation_text": {
        "type": "string",
        "description": "Solicitation clause text, RFP summary, or task description to evaluate"
      }
    }
  }

  arguments 16 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.