{"id":"io.github.MoltyCel/moltrust-mcp-server","slug":"io-github-moltycel-moltrust-mcp-server","title":"MolTrust MCP Server","description":"Verifiable agent identity and trust checks; MolCheck verdicts on mandates; Amazon Ads verdicts.","version":"1.3.1","publisher":{"kind":"github","id":"MoltyCel","label":"@MoltyCel on GitHub","url":"https://github.com/MoltyCel"},"website":"https://moltrust.ch/for-agents.html","repository":"https://github.com/MoltyCel/moltrust-mcp-server","remotes":[{"type":"streamable-http","url":"https://api.moltrust.ch/mcp","headers":[{"description":"Your MolTrust API key (authenticates identity/credits/register tools). Optional — read-only tools work without it.","value":"{api_key}","isSecret":true,"name":"X-API-Key"}]}],"packages":[],"published":"2026-11-15","updated":"2026-11-15","status":"online","auth":"","latency_ms":1254,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"moltrust_register","title":"","description":"Register a new AI agent on MolTrust.\n\n    Creates a decentralised identity (DID), issues a W3C Verifiable Credential,\n    and anchors the agent on the Base blockchain.\n\n    Args:\n        display_name: Agent name (1-64 chars, alphanumeric/dash/underscore/dot/space)\n        platform: Platform identifier (e.g. \"openai\", \"langchain\", \"custom\")\n    ","read_only":false},{"name":"moltrust_verify","title":"","description":"Verify an AI agent by its DID.\n\n    Checks whether the DID is registered and returns verification status\n    along with the agent's trust card (reputation, credentials, blockchain anchor).\n\n    Args:\n        did: Decentralised identifier (e.g. \"did:moltrust:a1b2c3d4e5f60718\")\n    ","read_only":true},{"name":"moltrust_reputation","title":"","description":"Get the reputation score for an AI agent.\n\n    Returns the aggregate trust score (1-5) and total number of ratings.\n\n    Args:\n        did: Decentralised identifier (e.g. \"did:moltrust:a1b2c3d4e5f60718\")\n    ","read_only":true},{"name":"moltrust_rate","title":"","description":"Rate another AI agent (1-5 stars).\n\n    Submit a trust rating from one agent to another.\n\n    Args:\n        from_did: Your agent's DID (the rater)\n        to_did: Target agent's DID (the agent being rated)\n        score: Rating from 1 (untrusted) to 5 (highly trusted)\n    ","read_only":false},{"name":"moltrust_credential","title":"","description":"Issue or verify a W3C Verifiable Credential.\n\n    Args:\n        action: Either \"issue\" or \"verify\"\n        subject_did: DID of the credential subject (required for \"issue\")\n        credential_type: Type of credential (default: \"AgentTrustCredential\", only for \"issue\")\n        credential: JSON string of the credential to verify (required for \"verify\")\n    ","read_only":false},{"name":"moltrust_credits","title":"","description":"Manage MolTrust credits: check balance, view pricing, transfer credits, or view transaction history.\n\n    Args:\n        action: One of \"balance\", \"pricing\", \"transfer\", or \"transactions\"\n        did: Agent DID (required for \"balance\" and \"transactions\")\n        to_did: Recipient DID (required for \"transfer\")\n        amount: Number of credits to transfer (required for \"transfer\", must be >= 1)\n    ","read_only":false},{"name":"moltrust_deposit_info","title":"","description":"Get USDC deposit instructions to buy MolTrust credits.\n\n    Returns the MolTrust wallet address on Base (Ethereum L2),\n    USDC token contract, conversion rate (1 USDC = 100 credits),\n    and step-by-step instructions.\n    ","read_only":true},{"name":"moltrust_claim_deposit","title":"","description":"Claim MolTrust credits from a USDC deposit on Base.\n\n    After sending USDC to the MolTrust wallet on Base (L2),\n    submit the transaction hash to receive credits.\n    1 USDC = 100 credits, verified on-chain.\n\n    Args:\n        tx_hash: Base blockchain transaction hash (0x...)\n        did: Your agent's DID to credit\n    ","read_only":false},{"name":"moltrust_stats","title":"","description":"Get MolTrust network statistics.\n\n    Returns total registered agents, credentials issued,\n    ratings given, and other network health metrics.\n    ","read_only":true},{"name":"moltrust_deposit_history","title":"","description":"Get USDC deposit history for an agent.\n\n    Args:\n        did: The agent's DID\n    ","read_only":true},{"name":"moltrust_erc8004","title":"","description":"Query the ERC-8004 on-chain agent registry on Base.\n\n    Resolve MolTrust agents to their on-chain ERC-8004 identity, fetch Agent Cards,\n    or look up on-chain agents by their agentId.\n\n    Args:\n        action: One of \"card\", \"resolve\", or \"well-known\"\n        did: Agent DID (required for \"card\", e.g. \"did:moltrust:a1b2c3d4e5f60718\")\n        agent_id: On-chain ERC-8004 agent ID (required for \"re","read_only":true},{"name":"moltguard_score","title":"","description":"Get an agent trust score for a Base wallet address.\n\n    Analyzes on-chain activity, ERC-8004 registration, USDC balance,\n    counterparty diversity, and MolTrust credentials to produce a 0-100 score.\n\n    Args:\n        address: Base (EVM) wallet address (0x...)\n    ","read_only":true},{"name":"moltguard_detail","title":"","description":"Get a detailed agent trust report for a Base wallet address.\n\n    Returns full scoring breakdown, wallet history from Blockscout,\n    ERC-8004 registration, MolTrust DID cross-reference, and Sybil indicators.\n\n    Args:\n        address: Base (EVM) wallet address (0x...)\n    ","read_only":true},{"name":"moltguard_sybil","title":"","description":"Scan a Base wallet for Sybil indicators.\n\n    Analyzes wallet age, transaction patterns, counterparty diversity,\n    and funding source to detect potential Sybil wallets.\n    Also traces funding clusters — if the funder sent ETH to many wallets,\n    it indicates a Sybil ring.\n\n    Args:\n        address: Base (EVM) wallet address (0x...)\n    ","read_only":true},{"name":"moltguard_market","title":"","description":"Check a Polymarket prediction market for integrity anomalies.\n\n    Analyzes volume spikes, price-volume divergence, liquidity ratios,\n    and outcome price spreads to detect potential manipulation.\n\n    Args:\n        market_id: Polymarket market/condition ID\n    ","read_only":true},{"name":"moltguard_feed","title":"","description":"Get the top anomaly feed — markets with highest integrity concerns.\n\n    Scans the top 20 active Polymarket markets by 24h volume and returns\n    those with anomaly indicators, sorted by anomaly score.\n    ","read_only":true},{"name":"moltguard_credential_issue","title":"","description":"Issue a W3C Verifiable Credential (AgentTrustCredential) for a wallet.\n\n    The credential contains the agent's trust score, Sybil score,\n    ERC-8004 registration status, and MolTrust verification status.\n    It is cryptographically signed with Ed25519 (JWS).\n\n    Args:\n        address: Base (EVM) wallet address (0x...)\n    ","read_only":false},{"name":"moltguard_credential_verify","title":"","description":"Verify a MoltGuard Verifiable Credential JWS signature.\n\n    Checks the Ed25519 signature and returns the credential payload if valid.\n\n    Args:\n        jws: JWS compact serialization string from a MoltGuard credential\n    ","read_only":true},{"name":"mt_shopping_info","title":"","description":"Get MT Shopping API information.\n\n    Returns the MT Shopping service info including version, supported\n    endpoints, BuyerAgentCredential schema, and verification details.\n    ","read_only":true},{"name":"mt_shopping_verify","title":"","description":"Verify a shopping transaction against a BuyerAgentCredential.\n\n    Checks the credential signature, spend limits, trust score, and\n    returns a verification receipt with approval status.\n\n    Args:\n        credential_jws: JWS compact serialization of the BuyerAgentCredential\n        transaction_amount: Transaction amount (e.g. 189.99)\n        transaction_currency: Currency code (e.g. \"USDC\")\n    ","read_only":true},{"name":"mt_shopping_issue_vc","title":"","description":"Issue a BuyerAgentCredential (W3C Verifiable Credential) for a shopping agent.\n\n    Creates a cryptographically signed credential that authorizes an AI agent\n    to make purchases on behalf of a human, with enforced spend limits.\n\n    Args:\n        agent_did: DID of the shopping agent (e.g. \"did:moltrust:agent123\")\n        human_did: DID of the authorizing human (e.g. \"did:moltrust:human456\")\n    ","read_only":false},{"name":"mt_travel_info","title":"","description":"Get MT Travel service information and available endpoints.\n\n    Returns service description, supported segments, and API endpoints\n    for the MT Travel booking trust protocol.\n    ","read_only":true},{"name":"mt_travel_verify","title":"","description":"Verify a travel booking against a TravelAgentCredential.\n\n    Runs a 10-step verification pipeline: VC signature, expiry, agent DID match,\n    segment authorization, spend limit, currency, daily cap, trust score,\n    delegation chain, and traveler binding.\n\n    Args:\n        agent_did: DID of the booking agent (e.g. \"did:base:0x...\")\n        vc_json: The TravelAgentCredential as a JSON string\n    ","read_only":true},{"name":"mt_travel_issue_vc","title":"","description":"Issue a TravelAgentCredential (W3C Verifiable Credential) for a booking agent.\n\n    Creates a cryptographically signed credential that authorizes an AI agent\n    to book travel on behalf of a principal (company/human), with enforced\n    segment permissions and spend limits.\n\n    Args:\n        agent_did: DID of the travel agent (e.g. \"did:base:0x...\")\n        principal_did: DID of the authorizing e","read_only":false},{"name":"mt_skill_audit","title":"","description":"Audit an AI agent skill (SKILL.md) for security risks.\n\n    Fetches the SKILL.md from a URL, computes its canonical SHA-256 hash,\n    and runs an 8-point security audit checking for prompt injection,\n    data exfiltration, tool scope violations, and metadata completeness.\n    Score starts at 100 with deductions per finding. Passing score: >= 70.\n\n    Args:\n        github_url: URL to the skill (Git","read_only":false},{"name":"mt_skill_verify","title":"","description":"Verify an AI agent skill by its canonical SHA-256 hash.\n\n    Checks if a VerifiedSkillCredential has been issued for this skill hash.\n    Returns credential details if verified.\n\n    Args:\n        skill_hash: Canonical skill hash (e.g. \"sha256:a1b2c3...\")\n    ","read_only":true},{"name":"mt_skill_issue_vc","title":"","description":"Issue a VerifiedSkillCredential for an AI agent skill.\n\n    Fetches SKILL.md, runs security audit, and if score >= 70, issues a\n    W3C Verifiable Credential signed with Ed25519 (JWS compact serialization).\n    Requires x402 payment ($5 USDC) when paywall is active.\n\n    Args:\n        author_did: DID of the skill author (e.g. \"did:base:0x...\")\n        repository_url: URL to the skill repository or","read_only":false},{"name":"mt_prediction_link","title":"","description":"Link a prediction market wallet and sync its track record.\n\n    Fetches trade history from Polymarket, calculates a prediction score (0-100),\n    and stores the wallet profile. Optionally links it to a MolTrust DID.\n\n    Args:\n        address: Prediction market wallet address (0x-prefixed, 42 chars)\n        platform: Platform name (default: \"polymarket\")\n        did: Optional MolTrust DID to link ","read_only":false},{"name":"mt_prediction_wallet","title":"","description":"Get prediction market profile and track record for a wallet.\n\n    Returns the prediction score (0-100), win/loss record, volume, ROI,\n    score breakdown, and recent market events.\n\n    Args:\n        address: Prediction market wallet address (0x-prefixed, 42 chars)\n    ","read_only":true},{"name":"mt_prediction_leaderboard","title":"","description":"Get the prediction market leaderboard — top wallets by prediction score.\n\n    Returns wallets ranked by their composite prediction score,\n    which factors in win rate, ROI, volume, sample size, and recency.\n\n    Args:\n        limit: Number of entries to return (default 20, max 100)\n    ","read_only":true},{"name":"mt_salesguard_verify","title":"","description":"Verify product provenance via MT Salesguard.\n\n    Checks whether a product ID has a valid ProductProvenanceCredential\n    issued by an authorized brand. Returns brand info, credential hash,\n    Base anchor, and risk level.\n\n    Args:\n        product_id: Product identifier (e.g. \"AIRMAX-90-WHITE-43\")\n    ","read_only":true},{"name":"mt_salesguard_reseller","title":"","description":"Verify reseller authorization via MT Salesguard.\n\n    Checks whether a reseller DID has been authorized by a brand\n    to sell specific products. Returns authorization status, brand info,\n    authorized SKUs, and expiry.\n\n    Args:\n        reseller_did: Reseller DID (e.g. \"did:web:sneakerstore.com\")\n    ","read_only":true},{"name":"mt_salesguard_register","title":"","description":"Register a brand with MT Salesguard.\n\n    Creates a new brand identity with a DID and API key.\n    The API key is used to authenticate product registration\n    and reseller authorization requests.\n\n    Args:\n        name: Brand name (e.g. \"Nike\", \"Adidas\")\n        domain: Brand domain (e.g. \"nike.com\")\n        contact_email: Contact email for the brand (optional)\n    ","read_only":false},{"name":"mt_fantasy_commit","title":"","description":"Commit a fantasy lineup with a SHA-256 hash anchored on Base L2.\n\n    Creates a FantasyLineupCredential (W3C VC) proving the lineup was\n    locked before contest start. The commitment hash is tamper-proof.\n\n    Args:\n        agent_did: Agent DID (e.g. \"did:moltrust:a1b2c3d4e5f67890\")\n        contest_id: Unique contest identifier (e.g. \"dk-nfl-sun-main-2026w12\")\n        platform: Platform name: dra","read_only":false},{"name":"mt_fantasy_verify","title":"","description":"Verify a fantasy lineup commitment. Public endpoint, no auth required.\n\n    Returns the full lineup, timing proof (minutes before contest),\n    on-chain verification status, and the FantasyLineupCredential.\n\n    Args:\n        commitment_hash: The 64-char SHA-256 commitment hash\n    ","read_only":true},{"name":"mt_fantasy_history","title":"","description":"Get fantasy lineup history and stats for an agent.\n\n    Returns ITM rate, ROI, projection accuracy, and recent lineups\n    for the specified agent DID.\n\n    Args:\n        did: Agent DID (e.g. \"did:moltrust:a1b2c3d4e5f67890\")\n    ","read_only":false},{"name":"mt_create_interaction_proof","title":"","description":"Create an interaction proof before issuing a SkillEndorsementCredential.\n\n    Returns evidence_hash and base_tx_hash anchored on Base L2.\n    Required before calling mt_endorse_agent. Valid for 72 hours.\n\n    Args:\n        api_key: MolTrust API key of the agent creating the proof\n        agent_a: DID of the first agent in the interaction\n        agent_b: DID of the second agent in the interaction\n","read_only":false},{"name":"mt_endorse_agent","title":"","description":"Issue a W3C SkillEndorsementCredential for another agent.\n\n    Requires a valid evidence_hash from mt_create_interaction_proof\n    (max 72h old). Self-endorsement is rejected.\n    Contributes to the endorsed agent's Trust Score.\n\n    Args:\n        endorser_api_key: MolTrust API key of the endorsing agent\n        endorsed_did: DID of the agent to endorse\n        skill: Skill being endorsed (python,","read_only":false},{"name":"mt_get_trust_score","title":"","description":"Get the Swarm Intelligence Trust Score for an agent (Phase 2).\n\n    Score combines direct endorsements, propagated trust from endorsers,\n    cross-vertical credential bonus, and interaction proof activity.\n    Returns null/withheld if fewer than 3 independent endorsers (non-seed).\n    Seed agents get their base score directly.\n\n    Args:\n        did: DID of the agent to score (e.g. \"did:moltrust:a","read_only":true},{"name":"mt_get_swarm_graph","title":"","description":"Get the trust propagation graph for an agent (2 hops).\n\n    Returns nodes (agents with scores) and edges (endorsements) showing\n    who endorses this agent and who endorses them.\n\n    Args:\n        did: DID of the agent to get graph for\n    ","read_only":true},{"name":"mt_get_swarm_stats","title":"","description":"Get global Swarm Intelligence statistics.\n\n    Returns total agents, endorsements, seed agents, average trust score,\n    propagation depth, and top trusted agents.\n    ","read_only":true},{"name":"mt_register_seed","title":"","description":"Register a trusted seed agent in the Swarm Intelligence network (admin only).\n\n    Seed agents bootstrap the trust network with a base score.\n    Requires the ADMIN_KEY for authorization.\n\n    Args:\n        did: DID of the agent to register as seed\n        label: Human-readable label for the seed agent\n        base_score: Base trust score (0-100, default 80)\n        admin_key: Admin key for author","read_only":false},{"name":"mt_get_badge","title":"","description":"Get the Verified by MolTrust badge status for an agent.\n\n    Returns badge tier, trust score, grade, issue/expiry dates,\n    and embeddable SVG URL.\n\n    Args:\n        did: The DID of the agent to check\n    ","read_only":true},{"name":"mt_issue_badge","title":"","description":"Issue a Verified by MolTrust badge for an agent.\n\n    Tiers: 'verified' (score 40+, $5), 'trusted' (score 60+, $20).\n    Badge is valid for 1 year and auto-revokes if trust score drops.\n\n    Args:\n        did: The DID of the agent to issue a badge for\n        tier: Badge tier — 'verified' or 'trusted'\n    ","read_only":false},{"name":"mt_check_badge","title":"","description":"Quick check: is this agent badge-verified by MolTrust?\n\n    Returns a simple yes/no with tier and expiry info.\n\n    Args:\n        did: The DID of the agent to check\n    ","read_only":true},{"name":"mt_issue_music_credential","title":"","description":"Issue a VerifiedMusicCredential for an AI-generated music track.\n\n    Creates a W3C Verifiable Credential proving the provenance of an\n    AI-generated music track — which tool created it, whether a human\n    was involved, and what rights apply. Anchored on Base L2.\n    EU AI Act Article 50(2) compliant.\n\n    Args:\n        agent_did: DID of the agent/creator (e.g. \"did:moltrust:abc123\")\n        to","read_only":false},{"name":"mt_verify_music_credential","title":"","description":"Verify a VerifiedMusicCredential by its ID.\n\n    Checks whether a music credential is valid (not revoked),\n    returns provenance summary including tool, human oversight,\n    rights, and on-chain anchor status.\n\n    Args:\n        credential_id: UUID of the music credential\n    ","read_only":true},{"name":"mt_get_track_provenance","title":"","description":"Get full provenance details for a music credential.\n\n    Returns the complete VerifiedMusicCredential including track\n    metadata, provenance hash, EU AI Act compliance status,\n    and on-chain anchor information.\n\n    Args:\n        credential_id: UUID of the music credential\n    ","read_only":true},{"name":"molcheck_verdict","title":"","description":"Verdict + per-check breakdown for an agent against its committed mandate.\n\n        Read-only. Recomputable from public chain data + the public mandate.\n\n        Args:\n            agent: agent address, did:moltrust / did:web, or ERC-8004 reference (public)\n        ","read_only":false},{"name":"moltproof_verdict","title":"","description":"Deprecated alias of molcheck_verdict; use that name. Verdict + per-check breakdown for an agent against its committed mandate.\n\n        Read-only. Recomputable from public chain data + the public mandate.\n\n        Args:\n            agent: agent address, did:moltrust / did:web, or ERC-8004 reference (public)\n        ","read_only":false},{"name":"molcheck_mandate","title":"","description":"The committed AAE mandate for an agent (venues, position cap, validity).\n\n        Read-only.\n\n        Args:\n            agent: public agent identifier (address / DID / ERC-8004 ref)\n        ","read_only":false},{"name":"moltproof_mandate","title":"","description":"Deprecated alias of molcheck_mandate; use that name. The committed AAE mandate for an agent (venues, position cap, validity).\n\n        Read-only.\n\n        Args:\n            agent: public agent identifier (address / DID / ERC-8004 ref)\n        ","read_only":false},{"name":"molcheck_evidence","title":"","description":"Verdict plus the decoded transactions that breached the mandate.\n\n        Read-only.\n\n        Args:\n            agent: public agent identifier (address / DID / ERC-8004 ref)\n        ","read_only":false},{"name":"moltproof_evidence","title":"","description":"Deprecated alias of molcheck_evidence; use that name. Verdict plus the decoded transactions that breached the mandate.\n\n        Read-only.\n\n        Args:\n            agent: public agent identifier (address / DID / ERC-8004 ref)\n        ","read_only":false},{"name":"molcheck_registry","title":"","description":"Agents with committed mandates and their current verdict.\n\n        Read-only. Ranks NO_MANDATE / NEEDS_REVIEW lower.\n        ","read_only":false},{"name":"moltproof_registry","title":"","description":"Deprecated alias of molcheck_registry; use that name. Agents with committed mandates and their current verdict.\n\n        Read-only. Ranks NO_MANDATE / NEEDS_REVIEW lower.\n        ","read_only":false},{"name":"molcheck_verify","title":"","description":"Recompute a verdict from public inputs and check its signature.\n\n        Offline and read-only: no DID/mandate/context is fetched here.\n\n        Args:\n            agent: public agent identifier\n            mandate: the public AAE Verifiable Credential\n            actions: public, already-decoded on-chain actions\n            signature: optional prior MolCheck signature to check\n        ","read_only":false},{"name":"moltproof_verify","title":"","description":"Deprecated alias of molcheck_verify; use that name. Recompute a verdict from public inputs and check its signature.\n\n        Offline and read-only: no DID/mandate/context is fetched here.\n\n        Args:\n            agent: public agent identifier\n            mandate: the public AAE Verifiable Credential\n            actions: public, already-decoded on-chain actions\n            signature: optional pr","read_only":false},{"name":"ads_onboard","title":"","description":"How an agent starts with MolTrust Ads: verdicts (allow / hold / forbid) on Amazon\n        Ads MCP tool calls before they run. Plans, key sign-up, SDK, endpoints. No input,\n        no account needed.\n        ","read_only":false},{"name":"ads_mandate_template","title":"","description":"Build an ads profile and its AAE mandate for one or more Amazon Ads accounts.\n\n        Pure: nothing is stored. Returns `profile` (pass it to ads_check) and `mandate`\n        (what /enforce/check evaluates).\n\n        Args:\n            account_ids: advertiserAccountId / profileId values the agent may act on\n            brands: brands the agent may touch\n            daily_budget_cap_usd: largest dai","read_only":false},{"name":"ads_check","title":"","description":"Allow / hold / forbid for one intended Amazon Ads MCP tool call, before it runs.\n\n        Needs your MolTrust API key as the X-API-Key header of the MCP connection (free key:\n        POST https://api.moltrust.ch/auth/signup). Counts against your plan like any check.\n        Never send Amazon credentials: they are refused.\n\n        Args:\n            profile: the `profile` object from ads_mandate_te","read_only":false},{"name":"canary_issue","title":"","description":"Issue a leak canary for one counterparty: a credential to hand to that counterparty.\n        If anyone else presents it at the MolTrust verifier, you get a signed leak event that\n        names the counterparty. Costs what a credential costs. Needs your MolTrust API key as\n        the X-API-Key header of the MCP connection.\n\n        Args:\n            counterparty_did: DID of the agent you hand the ","read_only":false},{"name":"canary_list","title":"","description":"Your leak canaries, newest first: counterparty, mode, reaction on leak and the number\n        of events so far. Paginated with limit/offset; `next_offset` is null on the last page.\n        Needs your MolTrust API key as X-API-Key on the MCP connection.\n        ","read_only":false},{"name":"canary_events","title":"","description":"Your leak events, newest first, each signed by MolTrust and carrying AER material\n        that `moltrust-verify` recomputes offline (trust list: GET /canary/trust-list).\n        Optionally for one canary. Needs your MolTrust API key as X-API-Key on the MCP\n        connection.\n\n        Args:\n            canary_id: only events of this canary (from canary_issue or canary_list)\n            limit: page","read_only":false}],"server_info":{"name":"moltrust","version":"1.30.0"},"category":"project","tags":["ecommerce","marketing","agents"],"kind":"remote","source":"registry","submitted":{},"first_party":false,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-02-24","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/io-github-moltycel-moltrust-mcp-server/"}