Trusteed MCP server
online · 100% uptimeio.github.trusteed-io/trusteed-mcp·v1.0.0CTEM for your Trusteed tenant: security summary, findings, compliance gaps, and scans via OAuth.
0 stars
Reviews
Write oneNobody has reviewed Trusteed yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Trusteed tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 204ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityOAuth resource metadata advertised on 40115/15
- Maintenancelast push 71 days ago12/15
- Maintainer identityregistry namespace matches repository owner6/10
How Trusteed compares
Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 85% of 915 Security servers
- Uptime
- 100%
- of our recent checks; the typical remote Security server answers 100%
- Response time
- 471 ms
- faster than 23% of 547 Security servers
Install Trusteed in Claude Code, Cursor or VS Code
claude mcp add --transport http trusteed-mcp https://mcp.trusteed.io/mcp
What the publisher says
From the Trusteed repository's README, as published. We do not edit it. Read it on GitHub
Trusteed Claude Marketplace
Official Trusteed plugins for Claude Code and Claude Cowork.
This repository is a Claude plugin marketplace. It packages the Trusteed remote MCP server so teams can install it with a single plugin command.
OAuth Client ID (required for Claude.ai connectors)
Trusteed uses a static public PKCE client (no secret). If Claude shows “Automatic client registration isn’t supported… add an OAuth Client ID”, paste:
f5f30ba8-da81-40ef-8e75-aaf98f75f324Claude.ai / Desktop custom connector
- Settings → Connectors → Add custom connector
- MCP URL: https://mcp.trusteed.io/mcp
- Advanced → OAuth Client ID: value above (leave Client Secret empty)
- Connect and sign in with an existing Trusteed portal account
Install (Claude Code plugin)
# Add this marketplace
/plugin marketplace add trusteed-io/trusteed-mcp-plugin
# Install the Trusteed MCP plugin
/plugin install trusteed-mcp@trusteedThen authenticate:
/mcpSelect trusteed, complete the browser login with your existing Trusteed portal account, and return to Claude.
Local development test
claude --plugin-dir ./plugins/trusteed-mcpPrerequisites
- An active Trusteed account (MCP does not create users).
- Claude Code (or Cowork) with plugin support.
- Network access to:
- https://mcp.trusteed.io (MCP resource server)
- https://app.trusteed.io (OAuth authorization server)
What you get
After install + OAuth, Claude can call Trusteed MCP tools for your tenant:
Read
- getsecuritysummary — high-level posture
- search_assets — inventory search
- listfindings / getfinding — vulnerabilities
- getcompliancestatus / listcontrolgaps — compliance
- explain_risk — narrative risk summary
- getscanstatus / getconnectionstatus — status
Write / action
- startscan / cancelscan — on-demand scans
- connectcloudaccount — hosted URL to connect cloud credentials (never through chat)
Bundled skills (examples):
- /trusteed-mcp:security-overview
- /trusteed-mcp:findings-triage
- /trusteed-mcp:connect-cloud
Repository layout
.claude-plugin/marketplace.json # marketplace catalog
plugins/trusteed-mcp/
.claude-plugin/plugin.json # plugin manifest
.mcp.json # remote MCP + OAuth
README.md # detailed plugin docs
skills/ # Claude skillsWebsite / how-to copy
Ready-to-publish page content (EN + TR) for Claude & ChatGPT setup:
- docs/website/connect-claude-chatgpt.en.md
- docs/website/connect-claude-chatgpt.tr.md
Privacy
Trusteed processes security and asset data for your tenant according to our privacy policy:
- https://trusteed.io/privacy (update if your public URL differs)
Cloud credentials are entered only on hosted Trusteed pages; they are never sent through the MCP chat channel.
Support
- Email: support@trusteed.io
- Product: https://trusteed.io
- MCP service source: https://gitlab.com/trusteed/trusteed-mcp-service
License
Apache-2.0 — see LICENSE.
Nothing above is checked by us. What we check is on the safety report.
Trusteed: common questions
- Is Trusteed MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Trusteed safety report
- How do I install Trusteed?
- It runs remotely at mcp.trusteed.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Trusteed need an API key?
- No key to paste: it signs you in with OAuth when your client connects.
- Is Trusteed maintained?
- The last commit was 110 days ago (2026-07-17). The latest release is v1.0.0.
- Is Trusteed up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Trusteed?
- Servers from other publishers that do the same job: Solana Security Standard MCP server, pkgxray MCP server and MCP ZAP Server MCP server.
- How does Trusteed compare with other Security MCP servers?
- safety score 88/100 (higher than 85% of 915 Security servers); uptime 100% (of our recent checks; the typical remote Security server answers 100%); response time 471 ms (faster than 23% of 547 Security servers). Full comparison.
Alternatives to Trusteed
Same job from other publishers: the closest match first, then the best rated.
- Solana Security StandardScan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.not reviewedGrowingA
- pkgxrayPre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.not reviewedGrowingB
MCP ZAP ServerSafe, self-hosted ZAP operator for guided AI security scans and reports.not reviewedGrowingB- Oauth AuditorScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audiencenot reviewedGrowingA
Sn1per MCP Server: pentest, recon and attack surface scanningRun scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.not reviewedGrowingA