MolTrust
MolTrust provides MCP tools for AI-agent identity, trust scoring, credential issuance/verification, and vertical-specific provenance and transaction checks.
Register and verify agents by DID, check reputation, rate agents, manage credits/USDC deposits, and query the ERC-8004 registry.
Issue and verify W3C Verifiable Credentials, including MoltGuard signed trust credentials.
Score Base wallets, produce detailed trust reports, and scan for Sybil indicators.
Detect Polymarket market integrity anomalies and view top anomaly feeds.
Verify shopping purchases and travel bookings against agent credentials, permissions, and spend limits.
Audit agent skills, issue/verify skill credentials, create interaction proofs, and endorse agents.
Link prediction-market wallets, show track records, and view leaderboards.
Commit, verify, and review fantasy lineup commitments anchored on Base.
Issue and verify music provenance credentials with EU AI Act-related metadata.
Register brands and verify product and reseller provenance.
Use Swarm Intelligence trust scores, trust graphs, network stats, and verified badges.
The hosted endpoint additionally offers MolCheck mandate-conformance tools and Amazon Ads allow/hold/forbid verdicts.
Provides tools to register AI agents on the OpenAI platform, enabling them to receive decentralized identifiers (DIDs) and Verifiable Credentials within the MolTrust trust infrastructure.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
MolTrust MCP Server
MCP server for MolTrust — Trust Infrastructure for AI Agents.
61 tools at the hosted endpoint https://api.moltrust.ch/mcp, across 13 areas: identity and credentials, on-chain trust scoring, mandate conformance, swarm intelligence, verified badges, autonomous commerce, booking trust, agent skill verification, prediction market track records, fantasy lineup commitments, music provenance, brand and reseller provenance, and Amazon Ads verdicts — all through the Model Context Protocol. The pip package carries 48 of them; the MolCheck verifier tools and the Amazon Ads tools run only at the hosted endpoint.
Tools
Identity & Credentials (11 tools)
moltrust_claim_deposit— Claim MolTrust credits from a USDC deposit on Base.moltrust_credential— Issue or verify a W3C Verifiable Credential.moltrust_credits— Manage MolTrust credits: check balance, view pricing, transfer credits, or view transaction history.moltrust_deposit_history— Get USDC deposit history for an agent.moltrust_deposit_info— Get USDC deposit instructions to buy MolTrust credits.moltrust_erc8004— Query the ERC-8004 on-chain agent registry on Base.moltrust_rate— Rate another AI agent (1-5 stars).moltrust_register— Register a new AI agent on MolTrust.moltrust_reputation— Get the reputation score for an AI agent.moltrust_stats— Get MolTrust network statistics.moltrust_verify— Verify an AI agent by its DID.
MoltGuard — Agent Trust Scoring (7 tools)
moltguard_credential_issue— Issue a W3C Verifiable Credential (AgentTrustCredential) for a wallet.moltguard_credential_verify— Verify a MoltGuard Verifiable Credential JWS signature.moltguard_detail— Get a detailed agent trust report for a Base wallet address.moltguard_feed— Get the top anomaly feed — markets with highest integrity concerns.moltguard_market— Check a Polymarket prediction market for integrity anomalies.moltguard_score— Get an agent trust score for a Base wallet address.moltguard_sybil— Scan a Base wallet for Sybil indicators.
MolCheck verifier — Mandate Conformance (5 tools, hosted endpoint only)
molcheck_evidence— Verdict plus the decoded transactions that breached the mandate.molcheck_mandate— The committed AAE mandate for an agent (venues, position cap, validity).molcheck_registry— Agents with committed mandates and their current verdict.molcheck_verdict— Verdict + per-check breakdown for an agent against its committed mandate.molcheck_verify— Recompute a verdict from public inputs and check its signature.
The former names moltproof_evidence, moltproof_mandate, moltproof_registry, moltproof_verdict and
moltproof_verify still answer as deprecated aliases of the same tools, so tools/list shows 10 entries here.
Swarm Intelligence (4 tools)
mt_get_swarm_graph— Get the trust propagation graph for an agent (2 hops).mt_get_swarm_stats— Get global Swarm Intelligence statistics.mt_get_trust_score— Get the Swarm Intelligence Trust Score for an agent (Phase 2).mt_register_seed— Register a trusted seed agent in the Swarm Intelligence network (admin only).
Verified Badges (3 tools)
mt_check_badge— Quick check: is this agent badge-verified by MolTrust?mt_get_badge— Get the Verified by MolTrust badge status for an agent.mt_issue_badge— Issue a Verified by MolTrust badge for an agent.
MT Shopping — Autonomous Commerce (3 tools)
mt_shopping_info— Get MT Shopping API information.mt_shopping_issue_vc— Issue a BuyerAgentCredential (W3C Verifiable Credential) for a shopping agent.mt_shopping_verify— Verify a shopping transaction against a BuyerAgentCredential.
MT Travel — Booking Trust (3 tools)
mt_travel_info— Get MT Travel service information and available endpoints.mt_travel_issue_vc— Issue a TravelAgentCredential (W3C Verifiable Credential) for a booking agent.mt_travel_verify— Verify a travel booking against a TravelAgentCredential.
MT Skills — Agent Skill Verification (5 tools)
mt_create_interaction_proof— Create an interaction proof before issuing a SkillEndorsementCredential.mt_endorse_agent— Issue a W3C SkillEndorsementCredential for another agent.mt_skill_audit— Audit an AI agent skill (SKILL.md) for security risks.mt_skill_issue_vc— Issue a VerifiedSkillCredential for an AI agent skill.mt_skill_verify— Verify an AI agent skill by its canonical SHA-256 hash.
MT Prediction — Market Track Records (3 tools)
mt_prediction_leaderboard— Get the prediction market leaderboard — top wallets by prediction score.mt_prediction_link— Link a prediction market wallet and sync its track record.mt_prediction_wallet— Get prediction market profile and track record for a wallet.
MT Sports — Fantasy Lineup Commitments (3 tools)
mt_fantasy_commit— Commit a fantasy lineup with a SHA-256 hash anchored on Base L2.mt_fantasy_history— Get fantasy lineup history and stats for an agent.mt_fantasy_verify— Verify a fantasy lineup commitment. Public endpoint, no auth required.
MT Music — Provenance (3 tools)
mt_get_track_provenance— Get full provenance details for a music credential.mt_issue_music_credential— Issue a VerifiedMusicCredential for an AI-generated music track.mt_verify_music_credential— Verify a VerifiedMusicCredential by its ID.
MT Salesguard — Brand & Reseller Provenance (3 tools)
mt_salesguard_register— Register a brand with MT Salesguard.mt_salesguard_reseller— Verify reseller authorization via MT Salesguard.mt_salesguard_verify— Verify product provenance via MT Salesguard.
MT Ads — Amazon Ads Verdicts (3 tools, hosted endpoint only)
ads_check— Allow / hold / forbid for one intended Amazon Ads MCP tool call, before it runs.ads_mandate_template— Build an ads profile and its AAE mandate for one or more Amazon Ads accounts.ads_onboard— How an agent starts with MolTrust Ads: verdicts (allow / hold / forbid) on Amazon Ads tool calls.
Related MCP server: Agent Identity Trust MCP
Setup
Get an API key at api.moltrust.ch/auth/signup. The read-only tools also work without one.
Hosted endpoint (all 61 tools)
The hosted endpoint is https://api.moltrust.ch/mcp (streamable HTTP). It serves
every tool, including the MolCheck verifier and Amazon Ads tools that the pip package
does not carry. Send the API key as the X-API-Key header.
Claude Code:
claude mcp add --transport http moltrust https://api.moltrust.ch/mcp \
--header "X-API-Key: your_api_key"Cursor (.cursor/mcp.json):
{
"mcpServers": {
"moltrust": {
"url": "https://api.moltrust.ch/mcp",
"headers": { "X-API-Key": "your_api_key" }
}
}
}OpenCode (opencode.json):
{
"mcp": {
"moltrust": {
"type": "remote",
"url": "https://api.moltrust.ch/mcp",
"enabled": true,
"headers": { "X-API-Key": "your_api_key" }
}
}
}The tool list and schemas are published at api.moltrust.ch/.well-known/mcp/server-card.json.
Local package (48 tools)
The sections below run the pip package locally over stdio with uvx. It carries 48
tools; the MolCheck verifier and Amazon Ads tools are only on the hosted endpoint.
Claude Code
claude mcp add moltrust -- uvx moltrust-mcp-serverSet your API key:
export MOLTRUST_API_KEY="your_api_key"Or add it permanently to Claude Code:
claude mcp add moltrust -e MOLTRUST_API_KEY=your_api_key -- uvx moltrust-mcp-serverClaude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"moltrust": {
"command": "uvx",
"args": ["moltrust-mcp-server"],
"env": {
"MOLTRUST_API_KEY": "your_api_key"
}
}
}
}Config file location:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor
Add to Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"moltrust": {
"command": "uvx",
"args": ["moltrust-mcp-server"],
"env": {
"MOLTRUST_API_KEY": "your_api_key"
}
}
}
}OpenCode
Add to opencode.json:
{
"mcp": {
"moltrust": {
"command": "uvx",
"args": ["moltrust-mcp-server"],
"env": {
"MOLTRUST_API_KEY": "your_api_key"
}
}
}
}pip install (manual)
pip install moltrust-mcp-serverThen run:
MOLTRUST_API_KEY=your_api_key moltrust-mcp-serverConfiguration
Environment Variable | Default | Description |
| — | Your MolTrust API key (required for register, rate, issue) |
|
| API base URL (for self-hosted instances) |
| — | Set to |
| — | Your existing MolTrust DID; when set, nothing is registered |
|
| Where the registered identity is stored |
|
| The |
Automatic DID registration
Since 1.3.0 the local package gives itself a MolTrust identity (a
did:moltrust: DID) on its first tool call, if it has none. This section says
exactly what that does, so you can decide whether you want it.
When it runs. Once per installation and API URL, on the first tool call of
the local stdio server. It does not run when MOLTRUST_API_KEY or
MOLTRUST_DID is set (you already have an identity), when the CI
environment variable is set, on the hosted HTTP endpoint, or when you opt out.
What is created. An Ed25519 key pair, generated on your machine. The private key never leaves it.
What is sent. Two requests to the API URL: GET /identity/register-challenge
and POST /identity/register-pop with the public key, a signature over the
challenge, a proof-of-work nonce, the display name mcp-server-<first 12 hex characters of the public key>, the platform usage-mcp, the source
mcp-server and the framework mcp. Nothing about your tools, prompts,
arguments or environment is sent. The registration is free and creates a
public registry entry for the DID, anchored on Base like any other
registration.
What is stored. The DID, the public key and the private key, in
~/.moltrust/mcp-identity.json with file mode 0600. Delete the file to forget
the identity; the next first call then registers a new one.
If it fails. One line on stderr, and the tool call goes on unchanged. The registration runs in the background and never delays or fails a tool call.
Opt out. Set MOLTRUST_NO_AUTO_REGISTER=1 in the server's environment, for
example in the env block of your MCP client configuration.
Examples
Once connected, you can ask your AI assistant:
"Register a new agent called 'my-assistant' on the 'openai' platform"
"Verify the agent with DID did:moltrust:a1b2c3d4e5f60718"
"What's the reputation of did:moltrust:a1b2c3d4e5f60718?"
"Rate agent did:moltrust:b2c3d4e5f6071890 with 5 stars"
"Get the trust score for wallet 0x1234...abcd"
"Scan wallet 0x1234...abcd for Sybil indicators"
"Check Polymarket market abc123 for anomalies"
"Issue a BuyerAgentCredential for my shopping agent"
"Verify this travel booking against the agent's credential"
"Audit this agent skill for security risks: https://github.com/example/skill"
"Link my Polymarket wallet 0x1234...abcd and show my prediction score"
"Show the prediction market leaderboard"
Development
git clone https://github.com/MoltyCel/moltrust-mcp-server.git
cd moltrust-mcp-server
pip install -e ".[dev]"
# Lint
ruff check src/
ruff format src/
# Type check
pyright src/
# Test
pytest tests/ -vSecurity Research
We regularly scan agent infrastructure for security issues and publish our findings:
We Scanned 50 Agent Endpoints — Here's What We Found — Common vulnerabilities in the agent ecosystem and how to fix them
License
MIT — CryptoKRI GmbH
Available Tools
48 toolsmoltguard_credential_issueBDestructiveInspect
Issue a W3C Verifiable Credential (AgentTrustCredential) for a wallet.
The credential contains the agent's trust score, Sybil score, ERC-8004 registration status, and MolTrust verification status. It is cryptographically signed with Ed25519 (JWS).
Args: address: Base (EVM) wallet address (0x...)
Inputs: address (required). Returns: result
moltguard_credential_verifyBRead-onlyInspect
Verify a MoltGuard Verifiable Credential JWS signature.
Checks the Ed25519 signature and returns the credential payload if valid.
Args: jws: JWS compact serialization string from a MoltGuard credential
Inputs: jws (required). Returns: result
moltguard_detailARead-onlyInspect
Get a detailed agent trust report for a Base wallet address.
Returns full scoring breakdown, wallet history from Blockscout, ERC-8004 registration, MolTrust DID cross-reference, and Sybil indicators.
Args: address: Base (EVM) wallet address (0x...)
Inputs: address (required). Returns: result
moltguard_feedARead-onlyInspect
Get the top anomaly feed — markets with highest integrity concerns.
Scans the top 20 active Polymarket markets by 24h volume and returns those with anomaly indicators, sorted by anomaly score.
Inputs: no named parameters. Returns: result
moltguard_marketARead-onlyInspect
Check a Polymarket prediction market for integrity anomalies.
Analyzes volume spikes, price-volume divergence, liquidity ratios, and outcome price spreads to detect potential manipulation.
Args: market_id: Polymarket market/condition ID
Inputs: market_id (required). Returns: result
moltguard_scoreARead-onlyInspect
Get an agent trust score for a Base wallet address.
Analyzes on-chain activity, ERC-8004 registration, USDC balance, counterparty diversity, and MolTrust credentials to produce a 0-100 score.
Args: address: Base (EVM) wallet address (0x...)
Inputs: address (required). Returns: result
moltguard_sybilARead-onlyInspect
Scan a Base wallet for Sybil indicators.
Analyzes wallet age, transaction patterns, counterparty diversity, and funding source to detect potential Sybil wallets. Also traces funding clusters — if the funder sent ETH to many wallets, it indicates a Sybil ring.
Args: address: Base (EVM) wallet address (0x...)
Inputs: address (required). Returns: result
moltrust_claim_depositADestructiveIdempotentInspect
Claim MolTrust credits from a USDC deposit on Base.
After sending USDC to the MolTrust wallet on Base (L2), submit the transaction hash to receive credits. 1 USDC = 100 credits, verified on-chain.
Args: tx_hash: Base blockchain transaction hash (0x...) did: Your agent's DID to credit
Inputs: did (required), tx_hash (required). Returns: result
moltrust_credentialCDestructiveInspect
Issue or verify a W3C Verifiable Credential.
Args: action: Either "issue" or "verify" subject_did: DID of the credential subject (required for "issue") credential_type: Type of credential (default: "AgentTrustCredential", only for "issue") credential: JSON string of the credential to verify (required for "verify")
Inputs: action (required), credential, subject_did, credential_type. Returns: result
moltrust_creditsBDestructiveInspect
Manage MolTrust credits: check balance, view pricing, transfer credits, or view transaction history.
Args: action: One of "balance", "pricing", "transfer", or "transactions" did: Agent DID (required for "balance" and "transactions") to_did: Recipient DID (required for "transfer") amount: Number of credits to transfer (required for "transfer", must be >= 1) reference: Optional reference string for transfers limit: Max transactions to return (default 20, for "transactions") offset: Pagination offset (default 0, for "transactions")
Inputs: action (required), did, limit, amount, +3 more. Returns: result
moltrust_deposit_historyCRead-onlyInspect
Get USDC deposit history for an agent.
Args: did: The agent's DID
Inputs: did (required). Returns: result
moltrust_deposit_infoARead-onlyInspect
Get USDC deposit instructions to buy MolTrust credits.
Returns the MolTrust wallet address on Base (Ethereum L2), USDC token contract, conversion rate (1 USDC = 100 credits), and step-by-step instructions.
Inputs: no named parameters. Returns: result
moltrust_erc8004ARead-onlyInspect
Query the ERC-8004 on-chain agent registry on Base.
Resolve MolTrust agents to their on-chain ERC-8004 identity, fetch Agent Cards, or look up on-chain agents by their agentId.
Args: action: One of "card", "resolve", or "well-known" did: Agent DID (required for "card", e.g. "did:moltrust:a1b2c3d4e5f60718") agent_id: On-chain ERC-8004 agent ID (required for "resolve", e.g. 21023)
Inputs: action (required), did, agent_id. Returns: result
moltrust_rateCDestructiveInspect
Rate another AI agent (1-5 stars).
Submit a trust rating from one agent to another.
Args: from_did: Your agent's DID (the rater) to_did: Target agent's DID (the agent being rated) score: Rating from 1 (untrusted) to 5 (highly trusted)
Inputs: score (required), to_did (required), from_did (required). Returns: result
moltrust_registerBDestructiveInspect
Register a new AI agent on MolTrust.
Creates a decentralised identity (DID), issues a W3C Verifiable Credential, and anchors the agent on the Base blockchain.
Args: display_name: Agent name (1-64 chars, alphanumeric/dash/underscore/dot/space) platform: Platform identifier (e.g. "openai", "langchain", "custom")
Inputs: platform (required), display_name (required). Returns: result
moltrust_reputationBRead-onlyInspect
Get the reputation score for an AI agent.
Returns the aggregate trust score (1-5) and total number of ratings.
Args: did: Decentralised identifier (e.g. "did:moltrust:a1b2c3d4e5f60718")
Inputs: did (required). Returns: result
moltrust_statsBRead-onlyInspect
Get MolTrust network statistics.
Returns total registered agents, credentials issued, ratings given, and other network health metrics.
Inputs: no named parameters. Returns: result
moltrust_verifyARead-onlyInspect
Verify an AI agent by its DID.
Checks whether the DID is registered and returns verification status along with the agent's trust card (reputation, credentials, blockchain anchor).
Args: did: Decentralised identifier (e.g. "did:moltrust:a1b2c3d4e5f60718")
Inputs: did (required). Returns: result
mt_check_badgeARead-onlyInspect
Quick check: is this agent badge-verified by MolTrust?
Returns a simple yes/no with tier and expiry info.
Args: did: The DID of the agent to check
Inputs: did (required). Returns: result
mt_create_interaction_proofAInspect
Create an interaction proof before issuing a SkillEndorsementCredential.
Returns evidence_hash and base_tx_hash anchored on Base L2. Required before calling mt_endorse_agent. Valid for 72 hours.
Args: api_key: MolTrust API key of the agent creating the proof agent_a: DID of the first agent in the interaction agent_b: DID of the second agent in the interaction interaction_type: Type of interaction (e.g. skill_verification, purchase, prediction) outcome: Outcome of the interaction: success or failure
Inputs: agent_a (required), agent_b (required), api_key (required), outcome, +1 more. Returns: result
mt_endorse_agentAIdempotentInspect
Issue a W3C SkillEndorsementCredential for another agent.
Requires a valid evidence_hash from mt_create_interaction_proof (max 72h old). Self-endorsement is rejected. Contributes to the endorsed agent's Trust Score.
Args: endorser_api_key: MolTrust API key of the endorsing agent endorsed_did: DID of the agent to endorse skill: Skill being endorsed (python, javascript, security, prediction, trading, data_analysis, api_integration, smart_contracts, nlp, computer_vision, general) evidence_hash: SHA-256 hash from mt_create_interaction_proof (sha256:...) evidence_timestamp: ISO 8601 timestamp from mt_create_interaction_proof vertical: MolTrust vertical (skill, shopping, travel, prediction, salesguard, sports, core)
Inputs: skill (required), vertical (required), endorsed_did (required), evidence_hash (required), +2 more. Returns: result
mt_fantasy_commitBDestructiveIdempotentInspect
Commit a fantasy lineup with a SHA-256 hash anchored on Base L2.
Creates a FantasyLineupCredential (W3C VC) proving the lineup was locked before contest start. The commitment hash is tamper-proof.
Args: agent_did: Agent DID (e.g. "did:moltrust:a1b2c3d4e5f67890") contest_id: Unique contest identifier (e.g. "dk-nfl-sun-main-2026w12") platform: Platform name: draftkings, fanduel, yahoo, sleeper, custom sport: Sport type: nfl, nba, mlb, nhl, pga, nascar, soccer, custom contest_start_iso: Contest start time in ISO 8601 (must be in the future) lineup_json: JSON string of lineup object (e.g. '{"QB":"Mahomes","RB1":"Henry"}') projected_score: Agent's projected score for this lineup confidence: Confidence level 0.0 to 1.0 entry_fee_usd: Contest entry fee in USD contest_type: Contest type (e.g. "classic", "showdown")
Inputs: sport (required), platform (required), agent_did (required), contest_id (required), +6 more. Returns: result
mt_fantasy_historyCDestructiveInspect
Get fantasy lineup history and stats for an agent.
Returns ITM rate, ROI, projection accuracy, and recent lineups for the specified agent DID.
Args: did: Agent DID (e.g. "did:moltrust:a1b2c3d4e5f67890")
Inputs: did (required). Returns: result
mt_fantasy_verifyARead-onlyInspect
Verify a fantasy lineup commitment. Public endpoint, no auth required.
Returns the full lineup, timing proof (minutes before contest), on-chain verification status, and the FantasyLineupCredential.
Args: commitment_hash: The 64-char SHA-256 commitment hash
Inputs: commitment_hash (required). Returns: result
mt_get_badgeBRead-onlyInspect
Get the Verified by MolTrust badge status for an agent.
Returns badge tier, trust score, grade, issue/expiry dates, and embeddable SVG URL.
Args: did: The DID of the agent to check
Inputs: did (required). Returns: result
mt_get_swarm_graphARead-onlyInspect
Get the trust propagation graph for an agent (2 hops).
Returns nodes (agents with scores) and edges (endorsements) showing who endorses this agent and who endorses them.
Args: did: DID of the agent to get graph for
Inputs: did (required). Returns: result
mt_get_swarm_statsBRead-onlyInspect
Get global Swarm Intelligence statistics.
Returns total agents, endorsements, seed agents, average trust score, propagation depth, and top trusted agents.
Inputs: no named parameters. Returns: result
mt_get_track_provenanceBRead-onlyInspect
Get full provenance details for a music credential.
Returns the complete VerifiedMusicCredential including track metadata, provenance hash, EU AI Act compliance status, and on-chain anchor information.
Args: credential_id: UUID of the music credential
Inputs: credential_id (required). Returns: result
mt_get_trust_scoreARead-onlyInspect
Get the Swarm Intelligence Trust Score for an agent (Phase 2).
Score combines direct endorsements, propagated trust from endorsers, cross-vertical credential bonus, and interaction proof activity. Returns null/withheld if fewer than 3 independent endorsers (non-seed). Seed agents get their base score directly.
Args: did: DID of the agent to score (e.g. "did:moltrust:a1b2c3d4e5f67890")
Inputs: did (required). Returns: result
mt_issue_badgeADestructiveInspect
Issue a Verified by MolTrust badge for an agent.
Tiers: 'verified' (score 40+, $5), 'trusted' (score 60+, $20). Badge is valid for 1 year and auto-revokes if trust score drops.
Args: did: The DID of the agent to issue a badge for tier: Badge tier — 'verified' or 'trusted'
Inputs: did (required), tier. Returns: result
mt_issue_music_credentialADestructiveInspect
Issue a VerifiedMusicCredential for an AI-generated music track.
Creates a W3C Verifiable Credential proving the provenance of an AI-generated music track — which tool created it, whether a human was involved, and what rights apply. Anchored on Base L2. EU AI Act Article 50(2) compliant.
Args: agent_did: DID of the agent/creator (e.g. "did:moltrust:abc123") tool: AI tool used (e.g. "Suno API v3.2", "Udio", "Magenta") human_oversight: "true", "false", or "partial" rights: Rights declaration (e.g. "CC-BY", "All Rights Reserved", "Agent-Wallet") track_title: Title of the track track_description: Optional description genre: Optional genre (e.g. "ambient", "jazz", "classical") isrc: Optional ISRC code (ISO 3901)
Inputs: tool (required), rights (required), agent_did (required), track_title (required), +4 more. Returns: result
mt_prediction_leaderboardARead-onlyInspect
Get the prediction market leaderboard — top wallets by prediction score.
Returns wallets ranked by their composite prediction score, which factors in win rate, ROI, volume, sample size, and recency.
Args: limit: Number of entries to return (default 20, max 100)
Inputs: limit. Returns: result
mt_prediction_linkAIdempotentInspect
Link a prediction market wallet and sync its track record.
Fetches trade history from Polymarket, calculates a prediction score (0-100), and stores the wallet profile. Optionally links it to a MolTrust DID.
Args: address: Prediction market wallet address (0x-prefixed, 42 chars) platform: Platform name (default: "polymarket") did: Optional MolTrust DID to link (e.g. "did:moltrust:a1b2c3d4e5f60718")
Inputs: address (required), did, platform. Returns: result
mt_prediction_walletBRead-onlyInspect
Get prediction market profile and track record for a wallet.
Returns the prediction score (0-100), win/loss record, volume, ROI, score breakdown, and recent market events.
Args: address: Prediction market wallet address (0x-prefixed, 42 chars)
Inputs: address (required). Returns: result
mt_register_seedAIdempotentInspect
Register a trusted seed agent in the Swarm Intelligence network (admin only).
Seed agents bootstrap the trust network with a base score. Requires the ADMIN_KEY for authorization.
Args: did: DID of the agent to register as seed label: Human-readable label for the seed agent base_score: Base trust score (0-100, default 80) admin_key: Admin key for authorization
Inputs: did (required), label (required), admin_key, base_score. Returns: result
mt_salesguard_registerBInspect
Register a brand with MT Salesguard.
Creates a new brand identity with a DID and API key. The API key is used to authenticate product registration and reseller authorization requests.
Args: name: Brand name (e.g. "Nike", "Adidas") domain: Brand domain (e.g. "nike.com") contact_email: Contact email for the brand (optional)
Inputs: name (required), domain (required), contact_email. Returns: result
mt_salesguard_resellerARead-onlyInspect
Verify reseller authorization via MT Salesguard.
Checks whether a reseller DID has been authorized by a brand to sell specific products. Returns authorization status, brand info, authorized SKUs, and expiry.
Args: reseller_did: Reseller DID (e.g. "did:web:sneakerstore.com")
Inputs: reseller_did (required). Returns: result
mt_salesguard_verifyARead-onlyInspect
Verify product provenance via MT Salesguard.
Checks whether a product ID has a valid ProductProvenanceCredential issued by an authorized brand. Returns brand info, credential hash, Base anchor, and risk level.
Args: product_id: Product identifier (e.g. "AIRMAX-90-WHITE-43")
Inputs: product_id (required). Returns: result
mt_shopping_infoBRead-onlyInspect
Get MT Shopping API information.
Returns the MT Shopping service info including version, supported endpoints, BuyerAgentCredential schema, and verification details.
Inputs: no named parameters. Returns: result
mt_shopping_issue_vcADestructiveInspect
Issue a BuyerAgentCredential (W3C Verifiable Credential) for a shopping agent.
Creates a cryptographically signed credential that authorizes an AI agent to make purchases on behalf of a human, with enforced spend limits.
Args: agent_did: DID of the shopping agent (e.g. "did:moltrust:agent123") human_did: DID of the authorizing human (e.g. "did:moltrust:human456") spend_limit: Maximum spend amount per transaction currency: Currency code (e.g. "USDC", "USD") categories: Comma-separated allowed categories (e.g. "electronics,books") validity_days: Number of days the credential is valid (default 30)
Inputs: currency (required), agent_did (required), human_did (required), categories (required), +2 more. Returns: result
mt_shopping_verifyARead-onlyInspect
Verify a shopping transaction against a BuyerAgentCredential.
Checks the credential signature, spend limits, trust score, and returns a verification receipt with approval status.
Args: credential_jws: JWS compact serialization of the BuyerAgentCredential transaction_amount: Transaction amount (e.g. 189.99) transaction_currency: Currency code (e.g. "USDC") merchant_id: Merchant identifier string item_description: Description of the item being purchased
Inputs: merchant_id (required), credential_jws (required), item_description (required), transaction_amount (required), +1 more. Returns: result
mt_skill_auditAIdempotentInspect
Audit an AI agent skill (SKILL.md) for security risks.
Fetches the SKILL.md from a URL, computes its canonical SHA-256 hash, and runs an 8-point security audit checking for prompt injection, data exfiltration, tool scope violations, and metadata completeness. Score starts at 100 with deductions per finding. Passing score: >= 70.
Args: github_url: URL to the skill (GitHub repo or direct HTTPS link to SKILL.md)
Inputs: github_url (required). Returns: result
mt_skill_issue_vcADestructiveInspect
Issue a VerifiedSkillCredential for an AI agent skill.
Fetches SKILL.md, runs security audit, and if score >= 70, issues a W3C Verifiable Credential signed with Ed25519 (JWS compact serialization). Requires x402 payment ($5 USDC) when paywall is active.
Args: author_did: DID of the skill author (e.g. "did:base:0x...") repository_url: URL to the skill repository or SKILL.md
Inputs: author_did (required), repository_url (required). Returns: result
mt_skill_verifyARead-onlyInspect
Verify an AI agent skill by its canonical SHA-256 hash.
Checks if a VerifiedSkillCredential has been issued for this skill hash. Returns credential details if verified.
Args: skill_hash: Canonical skill hash (e.g. "sha256:a1b2c3...")
Inputs: skill_hash (required). Returns: result
mt_travel_infoARead-onlyInspect
Get MT Travel service information and available endpoints.
Returns service description, supported segments, and API endpoints for the MT Travel booking trust protocol.
Inputs: no named parameters. Returns: result
mt_travel_issue_vcBDestructiveInspect
Issue a TravelAgentCredential (W3C Verifiable Credential) for a booking agent.
Creates a cryptographically signed credential that authorizes an AI agent to book travel on behalf of a principal (company/human), with enforced segment permissions and spend limits.
Args: agent_did: DID of the travel agent (e.g. "did:base:0x...") principal_did: DID of the authorizing entity (e.g. "did:base:acme-corp") segments: Comma-separated allowed segments (e.g. "hotel,flight,car_rental") spend_limit: Maximum spend amount per booking currency: Currency code (e.g. "USDC") traveler_name: Name of the authorized traveler (optional) validity_days: Number of days the credential is valid (default 30)
Inputs: currency (required), segments (required), agent_did (required), spend_limit (required), +3 more. Returns: result
mt_travel_verifyARead-onlyInspect
Verify a travel booking against a TravelAgentCredential.
Runs a 10-step verification pipeline: VC signature, expiry, agent DID match, segment authorization, spend limit, currency, daily cap, trust score, delegation chain, and traveler binding.
Args: agent_did: DID of the booking agent (e.g. "did:base:0x...") vc_json: The TravelAgentCredential as a JSON string merchant: Merchant domain (e.g. "hilton.com") segment: Booking segment: hotel, flight, car_rental, or rail amount: Booking amount currency: Currency code (e.g. "USDC")
Inputs: amount (required), segment (required), vc_json (required), currency (required), +2 more. Returns: result
mt_verify_music_credentialARead-onlyInspect
Verify a VerifiedMusicCredential by its ID.
Checks whether a music credential is valid (not revoked), returns provenance summary including tool, human oversight, rights, and on-chain anchor status.
Args: credential_id: UUID of the music credential
Inputs: credential_id (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 48 tools
Several trust-scoring tools overlap heavily: moltrust_reputation (1-5 DID score), moltguard_score (0-100 wallet score), moltguard_detail, mt_get_trust_score (swarm score), and moltrust_verify all answer variants of 'how trustworthy is this agent', differing mainly by identifier type and score scale. Badge tools are also blurry: mt_check_badge ('quick yes/no with tier') vs mt_get_badge ('tier, score, grade, expiry, SVG') are near-duplicates, and the generic moltrust_credential issue/verify coexists with moltguard_credential_issue/verify and per-vertical *_issue_vc tools.
Three different top-level prefixes coexist (moltrust_, moltguard_, mt_), and within the mt_ family verb ordering flips: mt_issue_badge / mt_get_badge / mt_create_interaction_proof (verb_noun) versus mt_skill_issue_vc / mt_travel_issue_vc / mt_fantasy_commit / mt_prediction_link (noun_verb). Some tools are also action-multiplexed (moltrust_credential, moltrust_credits, moltrust_erc8004), which breaks any single verb_noun reading.
48 tools is far beyond a comfortable surface for one server, even acknowledging the eight distinct verticals (shopping, travel, salesguard, fantasy, skills, prediction, music, swarm). Many of the count comes from near-duplicate trust/badge/credential tools rather than genuinely distinct operations.
Coverage is broad: identity registration, reputation/rating, credits and deposits, badges, swarm trust, and issue/verify pairs for every vertical, so most workflows have an entry point. Gaps are moderate — no credential/badge revocation, no agent deregistration, and no discovery/search or listing tool for agents outside fixed leaderboards.
Maintenance
Related MCP Connectors
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
AI Agent Trust Stack MCP: Veritas Proof-Chain Notary, Machine Credit Bureau, Firewall & Grader.
Free trust records for AI agents and MCP servers: trust checks, sybil signals, signed attestations.
MCP bridge to ERC-8004 on-chain agent identity, reputation and validation registries.
Related MCP Servers
- AlicenseAqualityDmaintenanceTrust intelligence MCP server for AI agents. 19 tools for identity stamps, reputation scoring (0-100), agent registry, forensic audit trails, ERC-8004 bridge, and A2A passports via x402 USDC micropayments.192Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAgent Identity Trust - MCP server providing AI-powered tools and automation by MEOK AI Labs10 npm158 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.31 PyPIMIT
- AlicenseAqualityBmaintenanceMCP server for checking supply-chain trust before connecting to AI agents, frameworks, or MCP servers.879 npm39 PyPI1MIT