HiveTrust MCP server
io.github.srotzin/hivetrustsrotzinstreamable-httpv1.0.0Scanned
KYA identity verification, trust scoring, and performance bonds for AI agents
17 tools: 1 can delete or cancel things, 12 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 11 findings
Tools listed without sign-in. Remote posture
Anlyon alternative
13 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the HiveTrust MCP server can do
The HiveTrust MCP server is published by the GitHub account srotzin. It has 17 tools. It can delete or cancel things (1 tool: hivetrust_revoke_credential) and create or change data (12 tools: hivetrust_register_agent, hivetrust_verify_identity, hivetrust_verify_agent_risk, hivetrust_ingest_telemetry and 8 more). 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 11 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Deletes or cancels 1Claude Code: deny
hivetrust_revoke_credentialRevoke a verifiable credential.3 findings
Why it is in this group
- The name "hivetrust_revoke_credential" says "revoke": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Revoke a verifiable credential. Records the revocation in the registry..."
- Info
The input schema at properties.credential_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_id.description: "UUID of the credential to revoke"
- Info
The input schema at properties.agent_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent UUID that owns the credential"
Description, as the server wrote it Revoke a verifiable credential. Records the revocation in the registry. Revoked credentials immediately fail verification checks.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
Changes things 12Claude Code: ask
hivetrust_bind_insuranceBind (activate) an insurance policy for an agent.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Bind (activate) an insurance policy for an agent. Locks in the premium, creates the policy record, and deploys the escrow contract on Base L2.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_create_leaseCreate a Data Oracle Context Lease — "Sign Once, Settle Many".No findings
Why it is in this group
- The name "hivetrust_create_lease" says "create": a word for a change.
Description, as the server wrote it Create a Data Oracle Context Lease — "Sign Once, Settle Many". Grants unlimited access to a data stream for a fixed period (24h/72h/168h). Returns a cryptographic lease token (SHA-256) for zero-friction verification. Available streams: construction_pricing, simpson_catalog, compliance_feeds, market_data, pheromone_signals.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_file_claimFile an insurance claim against an active policy.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it File an insurance claim against an active policy. Triggers claims adjudication workflow. Payouts are made in USDC via the Base L2 escrow contract.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_file_disputeFile a dispute or appeal against a trust score decision, credential revocation, or behavioral event.2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...appeal against a trust score decision, credential revocation, or behavioral event. Initia..."
- Info
The input schema at properties.target_type.enum[1] mentions "credential".
What this check looks forMatched text
inputSchema.properties.target_type.enum[1]: "credential"
Description, as the server wrote it File a dispute or appeal against a trust score decision, credential revocation, or behavioral event. Initiates the dispute resolution workflow.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_ingest_telemetryBulk ingest behavioral telemetry events for an agent.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Bulk ingest behavioral telemetry events for an agent. These events feed into the trust scoring engine. Supports transaction completions, SLA violations, dispute events, tool calls, and more.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_issue_credentialIssue a W3C-compatible verifiable credential to an agent.4 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Issue a W3C-compatible verifiable credential to an agent. Credentials represent veri..."
- Info
The input schema at properties.agent_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent UUID to issue the credential to"
- Info
The input schema at properties.credential_type.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_type.description: "Type of verifiable credential"
- Info
The input schema at properties.claims.description mentions "Credential".
What this check looks forMatched text
inputSchema.properties.claims.description: "Credential claims (key-value pairs specific to the..."
Description, as the server wrote it Issue a W3C-compatible verifiable credential to an agent. Credentials represent verified claims such as identity verification, compliance certification, or domain expertise.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_register_agentRegister a new AI agent identity with HiveTrust KYA (Know Your Agent).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Register a new AI agent identity with HiveTrust KYA (Know Your Agent). Assigns a unique agent ID, anchors the public key, and initializes the trust score.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_stake_bondStake USDC to back an agent's reputation via HiveBond.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Stake USDC to back an agent's reputation via HiveBond. Creates a trust bond with a specified tier (bronze/silver/gold/platinum) and lock period. Phase 1: declared stake amount tracked in-memory; flat $0.25 registration fee via x402. Longer lock periods earn higher simulated yield (2–5% APY). Slashing is permanent — if an agent fails, stake is slashed and paid to injured parties.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
hivetrust_verify_agent_riskQuick risk assessment for payment processors and marketplace operators.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Quick risk assessment for payment processors and marketplace operators. Returns verdict (ALLOW/REVIEW/BLOCK), trust tier, and max transaction limit. This is the free public endpoint — no API key required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
hivetrust_verify_bondQuick bond verification — check if an agent is bonded and at what tier.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Quick bond verification — check if an agent is bonded and at what tier. Returns bonded status, tier, staked amount, slash count, and max bounty access. This is the key integration point — other services call this to check bond status before assigning bounties. Free endpoint, no x402 payment required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
hivetrust_verify_credentialVerify a previously issued verifiable credential.2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Verify a previously issued verifiable credential. Checks signature validity, revocation..."
- Info
The input schema at properties.credential_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_id.description: "UUID of the credential to verify"
Description, as the server wrote it Verify a previously issued verifiable credential. Checks signature validity, revocation status, and expiration.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
hivetrust_verify_identityVerify an agent's cryptographic identity by checking public key ownership and checksum integrity.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Verify an agent's cryptographic identity by checking public key ownership and checksum integrity. Returns a verification result with confidence score and reason codes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
Only reads 4Show 4 read-only tools
hivetrust_get_agentRetrieve a registered agent's full identity profile, including public key, checksum, trust tier, capabilities, and compliance status.No findings
Why it is in this group
- The name "hivetrust_get_agent" says "get": a word for reading.
Description, as the server wrote it Retrieve a registered agent's full identity profile, including public key, checksum, trust tier, capabilities, and compliance status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
hivetrust_get_insurance_quoteGet a dynamic insurance premium quote for an agent transaction.No findings
Why it is in this group
- The name "hivetrust_get_insurance_quote" says "get": a word for reading.
Description, as the server wrote it Get a dynamic insurance premium quote for an agent transaction. Premium is calculated based on trust score, transaction value, and risk tier. HiveTrust takes a 1.5% spread on insured transactions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
hivetrust_get_platform_statsRetrieve HiveTrust platform-wide statistics: total registered agents, verified count, average trust score, total insured value, active policies, claims filed, and more.No findings
Why it is in this group
- The name "hivetrust_get_platform_stats" says "get": a word for reading.
Description, as the server wrote it Retrieve HiveTrust platform-wide statistics: total registered agents, verified count, average trust score, total insured value, active policies, claims filed, and more.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
hivetrust_get_trust_scoreRetrieve an agent's current multi-pillar trust score (0–1000 scale).No findings
Why it is in this group
- The name "hivetrust_get_trust_score" says "get": a word for reading.
Description, as the server wrote it Retrieve an agent's current multi-pillar trust score (0–1000 scale). Returns composite score, tier, per-pillar breakdown (identity, behavior, fidelity, compliance, provenance), verdict, and max recommended transaction value.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:11 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 13
- Protocol version
- 2024-11-05
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://hivetrust.onrender.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 13 tools that change things (1 destructive, 12 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://hivetrust.onrender.com/mcp: tools/list returned 17 tools to an anonymous client, including hivetrust_revoke_credential (destructive), hivetrust_register_agent (write), hivetrust_verify_identity (write), hivetrust_verify_agent_risk (write), hivetrust_ingest_telemetry (write) and 8 more
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "Issue a W3C-compatible verifiable credential to an agent. Credentials represent veri..."
The input schema at properties.agent_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent UUID to issue the credential to"
The input schema at properties.credential_type.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_type.description: "Type of verifiable credential"
The input schema at properties.claims.description mentions "Credential".
What this check looks forMatched text
inputSchema.properties.claims.description: "Credential claims (key-value pairs specific to the..."
The description mentions "credential".
What this check looks forMatched text
description: "Verify a previously issued verifiable credential. Checks signature validity, revocation..."
The input schema at properties.credential_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_id.description: "UUID of the credential to verify"
Show 5 more findingsShow fewer
The description mentions "credential".
What this check looks forMatched text
description: "Revoke a verifiable credential. Records the revocation in the registry..."
The input schema at properties.credential_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential_id.description: "UUID of the credential to revoke"
The input schema at properties.agent_id.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent UUID that owns the credential"
The description mentions "credential".
What this check looks forMatched text
description: "...appeal against a trust score decision, credential revocation, or behavioral event. Initia..."
The input schema at properties.target_type.enum[1] mentions "credential".
What this check looks forMatched text
inputSchema.properties.target_type.enum[1]: "credential"
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hivetrust https://hivetrust.onrender.com/mcpclaude mcp add --transport http hivetrust https://hivetrust.onrender.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__hivetrust__hivetrust_get_agent",
"mcp__hivetrust__hivetrust_get_trust_score",
"mcp__hivetrust__hivetrust_get_insurance_quote",
"mcp__hivetrust__hivetrust_get_platform_stats"
],
"ask": [
"mcp__hivetrust__hivetrust_register_agent",
"mcp__hivetrust__hivetrust_verify_identity",
"mcp__hivetrust__hivetrust_verify_agent_risk",
"mcp__hivetrust__hivetrust_ingest_telemetry",
"mcp__hivetrust__hivetrust_issue_credential",
"mcp__hivetrust__hivetrust_verify_credential",
"mcp__hivetrust__hivetrust_bind_insurance",
"mcp__hivetrust__hivetrust_file_claim",
"mcp__hivetrust__hivetrust_file_dispute",
"mcp__hivetrust__hivetrust_create_lease",
"mcp__hivetrust__hivetrust_stake_bond",
"mcp__hivetrust__hivetrust_verify_bond"
],
"deny": [
"mcp__hivetrust__hivetrust_revoke_credential"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as hivetrust. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.srotzin/hivetrust/verify?hash=c41e8bac9ae84277677f250f8b845c74c6d2dd8f751f8e3545de80238fecae17" | jq -e '.changed == false'Pinned hash c41e8bac9ae8, from Nov 20, 2026, 14:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.srotzin/hivetrust/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.srotzin/hivetrust)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.
HiveTrust MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the HiveTrust MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 13 of which can change, send or delete something, and 11 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the HiveTrust MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: hivetrust_revoke_credential.
Can the HiveTrust MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the HiveTrust MCP server have?
- 17 tools: 1 destructive, 12 write, 4 read. hivetrust_revoke_credential, hivetrust_register_agent, hivetrust_verify_identity, hivetrust_verify_agent_risk, hivetrust_ingest_telemetry, hivetrust_issue_credential, hivetrust_verify_credential, hivetrust_bind_insurance and 9 more.
Does the HiveTrust MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the HiveTrust MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the HiveTrust MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.