Skip to main content Trustvice is in restricted beta. At sign up or sign in, you have to provide the beta tester password you received or request one at preview@trustvice.com . Thank you. Products Agents
Watch, test and rehearse what agents do.
Every plan reaches every suite; plans differ by capacity.
All 16 suites → Pricing → Governance
Rules, drift and behaviour checks.
Every plan reaches every suite; plans differ by capacity.
All 16 suites → Pricing → Nexus nexus Ten policy and trust engines for agent behaviour, with combo templates. Tranquility tranquility Goals, evidence coverage, service-level objectives and analytics over the evidence you already hold. Driftvice driftvice Semantic drift detection and a canon workbench for monitored surfaces. Paradigm paradigm A behavioural truth layer: consent, idiom, temperament, overture, rapport, counterfact, umbra, survey and breaker. One operation counts as four evidence calls. Commerce and disclosure
Price provenance and AI disclosure.
Every plan reaches every suite; plans differ by capacity.
All 16 suites → Pricing → Interfaces
How people and agents reach the platform.
Every plan reaches every suite; plans differ by capacity.
All 16 suites → Pricing → Agentic API agentic-api One endpoint, POST /api/v1/actions/<id>, for every declared action, with a fifteen-step pipeline. OneMCP onemcp A stateless MCP server that projects the Agentic API catalogue as tools, with the MCP bridge for confirmation apps. Number One number-one A constrained assistant with Calculator, Analyst and Admin modes, a memory ledger and bring-your-own-key on Team and above. Lens lens A declarative query language run against the audit chain, producing a signed evidence bundle. Portmind portmind Portable, verifiable agent memory: key-value, snapshot, export, import with verification and mandates. Capabilities
Built into Trustvice 360: signed, chained, publicly verifiable records for the systems you connect. Powered by Entpoind technology.
Every plan reaches every suite; plans differ by capacity.
All 16 suites → Pricing → Integrations
Connect Trustvice to the tools you already use. One MCP server and one Agentic API, behind the same gateway. Connect an AI client or your own backend to the Trustvice 360 action catalogue.
16 Trustvice 360 suites behind one gateway Start free
Declare the rules. Have every run checked. Agents, evidence, governance, commerce and disclosure are all in Trustvice 360. Sign up free and open every suite from one dashboard.
Trustvice 360 dashboard demo
MCP and the Agentic API
Public keys, offline verification Where calls come from
One gateway
Authenticates the credential, checks the action's permissions, applies rate limits and writes the audit entry. The same checks for every transport.
One response envelope
ok and data on success, or an error with a machine-readable code, on every transport.
Anyone can verify
Signed records verify against Trustvice's published public keys. No account needed.
How to read this directory Each entry says what exists today. Where something is not published yet, we say so and show the way that works now.
Hosted service Runs on Trustvice. Point your client at the address and authenticate.
Published A package or file you can download from a public registry or URL today.
Not published yet The source is complete but not released. Use the alternative shown on the card.
Manifest only A description file is published for hosts that read it. We do not document install steps. Start here
Three ways to start Connect an assistant over MCP, call the Agentic API from your code, or verify signed records yourself.
MCP server Hosted service Gives Claude, Cursor, ChatGPT and any client that speaks streamable HTTP the Trustvice 360 actions as tools, projected from the Agentic API catalogue.
Stateless JSON-RPC over HTTP POST, protocol version 2025-06-18 Workspace key, personal token or OAuth with PKCE The same permissions and confirmations as the Agentic API Directory
Every way to connect Filter by category. Each card gives the setup in a few lines and links to the page with the full steps.
All21 AI clients6 SDKs and libraries1 APIs and specs4 Discovery files10
Showing 21 of 21
Claude Code AI clients Hosted service
Adds Trustvice as a remote HTTP MCP server; sign in with OAuth through the /mcp command.
Agent frameworks and platforms
These frameworks and platforms can call Trustvice through its MCP server or the Agentic API, in the same way as any other client.
LangChain Salesforce Agentforce Build your own
No integration for your stack? Call the API. Trustvice is plain JSON over HTTPS. Everything an integration does is one request, and a verifier is four steps you can write in any language.
Before you connect
The same rules for every integration 01 One gateway MCP and Agentic API calls are authenticated, permission-checked, rate-limited and audited in the same way.
02 Least privilege Every action declares the permissions it needs. Grant a credential only what its job requires.
03 Confirmation for risky actions Destructive and billing actions return 412 confirmation_required first; the caller mints a short-lived confirmation token before retrying.
04
Missing an integration? Tell us which client, platform or pipeline you want to connect and what you need it to record.
The names and logos of Bedrock AgentCore are trademarks or registered trademarks of Amazon.com, Inc. or its affiliates. The names and logos of ChatGPT, OpenAI, OpenAI Codex, ChatGPT agent and OpenAI Agents SDK are trademarks or registered trademarks of OpenAI. The names and logos of Claude Code, Claude and Claude Agent SDK are trademarks or registered trademarks of Anthropic, PBC. The names and logos of Cline are trademarks or registered trademarks of Cline Bot Inc. The names and logos of CrewAI are trademarks or registered trademarks of CrewAI, Inc. The names and logos of Cursor are trademarks or registered trademarks of Anysphere, Inc. The names and logos of Devin are trademarks or registered trademarks of Cognition AI, Inc. The names and logos of Gemini, Gemini Enterprise, Google ADK and Gemini CLI are trademarks or registered trademarks of Google LLC. The names and logos of GitHub Copilot are trademarks or registered trademarks of GitHub, Inc. The names and logos of IBM watsonx Orchestrate are trademarks or registered trademarks of International Business Machines Corporation. The names and logos of Intercom Fin are trademarks or registered trademarks of Intercom, Inc. The names and logos of LangChain are trademarks or registered trademarks of LangChain, Inc. The names and logos of LlamaIndex are trademarks or registered trademarks of LlamaIndex, Inc. The names and logos of Manus are trademarks or registered trademarks of Manus AI. The names and logos of Mastra are trademarks or registered trademarks of Mastra. The names and logos of Microsoft Copilot Studio and Microsoft Agent Framework are trademarks or registered trademarks of Microsoft Corporation. The names and logos of Model Context Protocol are trademarks or registered trademarks of The Linux Foundation. The names and logos of n8n are trademarks or registered trademarks of n8n GmbH. The names and logos of OpenClaw are trademarks or registered trademarks of the OpenClaw project. The names and logos of Perplexity and Perplexity Comet are trademarks or registered trademarks of Perplexity AI, Inc. The names and logos of Pydantic AI are trademarks or registered trademarks of Pydantic Services Inc. The names and logos of Replit Agent are trademarks or registered trademarks of Replit, Inc. The names and logos of Salesforce Agentforce are trademarks or registered trademarks of Salesforce, Inc. Developers Programs Social Media Legal Terms Privacy Right of withdrawal Imprint GDPR & Opt-Out Do not sell / share Report abuse Trademarks ✕ Trademarks Notice Trustvice Tools work with these AI models, platforms and agents through the Trustvice REST API and MCP server. Their names and logos are shown only to say so. It does not mean that any of these companies endorses, sponsors or partners with Trustvice.
The names and logos of Amazon Bedrock and Bedrock AgentCore are trademarks or registered trademarks of Amazon.com, Inc. or its affiliates. The names and logos of Anthropic, Claude Code and Claude Agent SDK are trademarks or registered trademarks of Anthropic, PBC. The names and logos of Azure AI Foundry, Microsoft Copilot Studio and Microsoft Agent Framework are trademarks or registered trademarks of Microsoft Corporation. The names and logos of Cline are trademarks or registered trademarks of Cline Bot Inc. The names and logos of Cohere are trademarks or registered trademarks of Cohere Inc. The names and logos of CrewAI are trademarks or registered trademarks of CrewAI, Inc. The names and logos of Cursor are trademarks or registered trademarks of Anysphere, Inc. The names and logos of DeepSeek are trademarks or registered trademarks of DeepSeek. The names and logos of Devin are trademarks or registered trademarks of Cognition AI, Inc. The names and logos of GitHub Copilot are trademarks or registered trademarks of GitHub, Inc. The names and logos of Google Gemini, Vertex AI, Gemini Enterprise, Google ADK and Gemini CLI are trademarks or registered trademarks of Google LLC. The names and logos of Hugging Face are trademarks or registered trademarks of Hugging Face, Inc. The names and logos of IBM watsonx Orchestrate are trademarks or registered trademarks of International Business Machines Corporation. The names and logos of Intercom Fin are trademarks or registered trademarks of Intercom, Inc. The names and logos of LangChain are trademarks or registered trademarks of LangChain, Inc. The names and logos of LlamaIndex are trademarks or registered trademarks of LlamaIndex, Inc. The names and logos of Manus are trademarks or registered trademarks of Manus AI. The names and logos of Mastra are trademarks or registered trademarks of Mastra. The names and logos of Meta Llama are trademarks or registered trademarks of Meta Platforms, Inc. The names and logos of Mistral AI are trademarks or registered trademarks of Mistral AI. The names and logos of Model Context Protocol and Agent2Agent are trademarks or registered trademarks of The Linux Foundation. The names and logos of n8n are trademarks or registered trademarks of n8n GmbH. The names and logos of Ollama are trademarks or registered trademarks of Ollama. The names and logos of OpenAI, OpenAI Codex, ChatGPT agent and OpenAI Agents SDK are trademarks or registered trademarks of OpenAI. The names and logos of OpenClaw are trademarks or registered trademarks of the OpenClaw project. The names and logos of OpenRouter are trademarks or registered trademarks of OpenRouter, Inc. The names and logos of Perplexity and Perplexity Comet are trademarks or registered trademarks of Perplexity AI, Inc. The names and logos of Pydantic AI are trademarks or registered trademarks of Pydantic Services Inc. The names and logos of Qwen are trademarks or registered trademarks of Alibaba Cloud. The names and logos of Replit Agent are trademarks or registered trademarks of Replit, Inc. The names and logos of Salesforce Agentforce are trademarks or registered trademarks of Salesforce, Inc. The names and logos of SAP Joule are trademarks or registered trademarks of SAP SE. The names and logos of ServiceNow AI Agents are trademarks or registered trademarks of ServiceNow, Inc. The names and logos of UiPath are trademarks or registered trademarks of UiPath, Inc. The names and logos of Vercel AI SDK are trademarks or registered trademarks of Vercel, Inc. The names and logos of xAI Grok are trademarks or registered trademarks of xAI. All other trademarks, product names and logos are the property of their respective owners.
Logo artwork from LobeHub Icons (MIT licence) and Simple Icons (CC0). The Salesforce Agentforce, ServiceNow and Agent2Agent logos are the marks their owners publish. The licences cover the artwork files, not the trademarks they show.
All legal documents Tech stack © 2026 Trustvice. All rights reserved.
curl -sS https://mcp.trustvice.com/mcp \
-H "Authorization: Bearer $TRUSTVICE_TOKEN" \
-H "Content-Type: application/json" \
-d '{ "jsonrpc": "2.0", "id": 2, "method": "tools/list" }'
Agentic API Hosted service One endpoint for every declared action: POST /api/v1/actions/<id>, with a typed input and a uniform response envelope.
The public catalogue is served at GET /api/v1/actions, with no credential Every action declares a safety level: read, write, destructive or billing_impacting Destructive and billing actions ask for a short-lived confirmation token first HTTP
POST /api/v1/actions/<action-id>
Authorization: Bearer <oauth-access-token>
X-Workspace-Id: ws_…
Content-Type: application/json
{ …input fields… }
→ { "ok": true, "data": { …action output… } }Agentic actions
Verifier library (not published yet) Not published yet Verifies signed receipts, Notarian evidence bundles, TOPS seals and audit-chain exports with WebCrypto alone, fully offline. Until it is on the npm registry, use the verify page.
Zero dependencies Returns bad_signature, unknown_key or malformed_envelope when a check fails A valid signature proves integrity and origin, not that a claim inside is true verify.ts
import { verifyArtifactWithKeys } from "@trustvice/verify";
const jwks = await (await fetch("https://api.trustvice.com/.well-known/trustvice-keys.json")).json();
const verdict = await verifyArtifactWithKeys(receipt, jwks);
if (!verdict.ok) throw new Error(verdict.reason);Open the verify page bash
claude mcp add --transport http trustvice https://mcp.trustvice.com/mcpClaude on the web and desktop AI clients Hosted service
Connects as a custom connector over OAuth with PKCE.
Claude
Settings → Connectors → Add custom connector
Name: Trustvice
URL: https://mcp.trustvice.com/mcp
Then: Connect, sign in with your Trustvice accountRead the docs Cursor AI clients Hosted service
Reads the server from mcp.json for all projects or one, then signs in with OAuth or sends a key from your environment.
~/.cursor/mcp.json
{
"mcpServers": {
"trustvice": {
"url": "https://mcp.trustvice.com/mcp"
}
}
}Read the docs ChatGPT AI clients Hosted service
Connects as a custom connector in developer mode with OAuth, where your plan and workspace admin allow it.
ChatGPT
Settings → Connectors → Advanced → Developer mode
Create → Name: Trustvice
MCP server URL: https://mcp.trustvice.com/mcp
Authentication: OAuth → Create → ConnectRead the docs OpenAI Responses API AI clients Hosted service
Uses Trustvice as a remote MCP tool from scripts; keep require_approval set to always so a person approves each action.
json
{
"type": "mcp",
"server_label": "trustvice",
"server_url": "https://mcp.trustvice.com/mcp",
"authorization": "<OAuth access token>",
"require_approval": "always"
}Read the docs VS Code and other MCP clients AI clients Hosted service
Any client that supports remote HTTP servers with custom headers can connect. Send the X-Workspace-Id header with your credential.
MCP
type http (streamable HTTP)
url https://mcp.trustvice.com/mcp
header Authorization: Bearer <credential>
header X-Workspace-Id: ws_…Read the docs @trustvice/verify (not published yet) SDKs and libraries Not published yet
Verifies a signed record against a key set you pass in, with no network call. Not on the npm registry yet; the verify page works today.
ts
import { verifyArtifactWithKeys } from "@trustvice/verify";
const verdict = await verifyArtifactWithKeys(receipt, jwks);
console.log(verdict.ok ? verdict.kind : verdict.reason);Open the verify page Agentic API APIs and specs Hosted service
Every declared action as one POST over plain HTTP, the same catalogue the MCP server projects as tools.
bash
curl -sS -X POST https://api.trustvice.com/v1/actions/trustactor.runs.list \
-H "Authorization: Bearer $TRUSTVICE_TOKEN" \
-H "X-Workspace-Id: ws_…" \
-H "Content-Type: application/json" -d '{}'Read the docs Action catalogue APIs and specs Hosted service
The public, self-describing list of registered actions, served anonymously.
bash
curl -s https://api.trustvice.com/v1/actionsRead the docs OpenAPI 3.1 document APIs and specs Published
Describes the action API, its schemas and security schemes, at /openapi.json and the well-known path.
bash
curl -s https://360.trustvice.com/openapi.json -o trustvice-openapi.json
# also at /.well-known/openapi.jsonRead the docs Public signing keys APIs and specs Published
The Ed25519 public keys that sign receipts, as a JSON key set.
bash
curl -sSL https://360.trustvice.com/.well-known/receipt-keys.jsonOpen the file llms.txt Discovery files Published
A plain-text map of the site and every docs page, so a language model can choose what to read.
GET
https://360.trustvice.com/llms.txtOpen the file AGENTS.md Discovery files Published
One Markdown document with the hosts, authentication and every action with an example, for coding assistants.
GET
https://360.trustvice.com/AGENTS.mdOpen the file MCP server manifests Discovery files Published
server.json and tools.json describe the endpoint, authentication modes and tool list without opening a connection.
GET
https://360.trustvice.com/.well-known/mcp/server.json
https://360.trustvice.com/.well-known/mcp/tools.jsonOpen the file Agent card Discovery files Published
The gateway agent's DID, transports, authentication and one capability per action, also at a2a.json.
GET
https://360.trustvice.com/.well-known/agent-card.json
https://360.trustvice.com/.well-known/agents.jsonOpen the file OAuth metadata Discovery files Published
OpenID and authorization-server metadata, so a client can find the endpoints and run the PKCE flow.
GET
https://360.trustvice.com/.well-known/openid-configuration
https://360.trustvice.com/.well-known/oauth-authorization-serverOpen the file ChatGPT app manifest Discovery files Manifest only
Describes the actions and OAuth endpoints for ChatGPT connectors, also at ai-plugin.json.
GET
https://360.trustvice.com/.well-known/chatgpt-app.jsonOpen the file Gemini extension manifest Discovery files Manifest only
Describes the actions as function declarations for Gemini extension tooling. Install steps are not documented.
GET
https://360.trustvice.com/.well-known/gemini-extension.jsonOpen the file Perplexity connector manifest Discovery files Manifest only
Describes each action with its HTTP endpoint for Perplexity connectors. Install steps are not documented.
GET
https://360.trustvice.com/.well-known/perplexity-connector.jsonOpen the file Claude connector manifest Discovery files Manifest only
Names the MCP endpoint and OAuth settings for Claude connectors. The documented route is the custom connector above.
GET
https://360.trustvice.com/.well-known/claude-cowork.jsonOpen the file NLWeb Discovery files Manifest only
Maps natural-language intents to action ids, with the MCP and REST endpoints and a safety level for each.
GET
https://360.trustvice.com/.well-known/nlweb.jsonOpen the file The manifest files describe the Agentic API action catalogue and some still carry older wording, such as audit-log actions, permission names listed as scopes and DPoP described as required. Where a file and the docs disagree, follow the docs.
OpenClaw Claude Code CrewAI Microsoft Copilot Studio OpenAI Codex LlamaIndex ServiceNow AI Agents ChatGPT agent Cursor OpenAI Agents SDK Gemini Enterprise Manus GitHub Copilot Claude Agent SDK Bedrock AgentCore Perplexity Comet Devin Google ADK SAP Joule Gemini CLI Microsoft Agent Framework IBM watsonx Orchestrate Cline Vercel AI SDK UiPath Replit Agent Mastra Intercom Fin Pydantic AI n8n Showing a name or logo here means only that the product can reach Trustvice through MCP or the REST API. It does not mean that its owner endorses, sponsors or partners with Trustvice.
What every verifier does 01 Remove the signature member from the receipt and keep the rest. 02 Serialise what is left in RFC 8785 canonical form: keys sorted, no whitespace. 03 Find the key whose kid equals the receipt's signatureKeyId in the published key set. None means unknown_key. 04 Check the Ed25519 signature over those bytes with that key. A mismatch means bad_signature.
Keys stay server side Keep credentials in environment variables or a secret manager, never in front-end code or prompts.
The names and logos of SAP Joule are trademarks or registered trademarks of SAP SE.
The names and logos of ServiceNow AI Agents are trademarks or registered trademarks of ServiceNow, Inc.
The names and logos of UiPath are trademarks or registered trademarks of UiPath, Inc.
The names and logos of Vercel AI SDK are trademarks or registered trademarks of Vercel, Inc. All other trademarks, product names and logos are the property of their respective owners.
AI clients over MCP
LangChain
Salesforce Agentforce
MCP and HTTP
OpenClaw
Claude Code
CrewAI
Microsoft Copilot Studio
OpenAI Codex
LlamaIndex
ServiceNow AI Agents
ChatGPT agent
Cursor
Gemini Enterprise
Manus
GitHub Copilot
Claude Agent SDK
Bedrock AgentCore
Perplexity Comet
Devin
Google ADK
SAP Joule
Gemini CLI
Microsoft Agent Framework
IBM watsonx Orchestrate
Cline
Vercel AI SDK
UiPath
Replit Agent
Mastra
Intercom Fin
Pydantic AI
n8n