Back to Browse

Veriswarm Sdk MCP Server

Developer ToolsUse Caution4.8MCP RegistryLocal
Free

Server data from the Official MCP Registry

VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol

About

VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol

Security Report

4.8
Use Caution4.8High Risk

The VeriSwarm MCP server is a legitimate trust-infrastructure client that sends its API key and, by default, MCP tool arguments and responses to api.veriswarm.ai for PII tokenization, which matches its stated purpose. It enforces HTTPS for credentialed requests, stores credentials in a 0600 file, and fails closed on scan errors. The main concerns are that the setup CLI writes the API key in plaintext into the client's settings.json, that the opt-in GUARD_SECRETS_DETECTION mode sends unredacted secrets to the third-party API, and that the truncated hook code could not be fully reviewed. Supply chain analysis found 5 known vulnerabilities in dependencies (0 critical, 5 high severity). Package verification found 1 issue.

10 files analyzed · 11 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

env_vars

Check that this permission is expected for this type of plugin.

process_spawn

Check that this permission is expected for this type of plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "veriswarm-mcp": {
      "command": "uvx",
      "args": [
        "veriswarm-mcp==0.6.0"
      ]
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

VeriSwarm SDK & Integrations

pip veriswarm pip veriswarm-mcp npm @veriswarm/sdk MCP Registry

Official client libraries, MCP server, and plugins for VeriSwarm — trust infrastructure for AI agents.

Packages

PackageLanguageInstallDescription
Python SDKPythonpip install veriswarmREST client with Workflows, credential issuance, scoring profiles, LangChain adapter
Node.js SDKJavaScriptnpm install @veriswarm/sdkESM client for decisions, events, Workflows, agent management
MCP ServerPythonpip install veriswarm-mcp102 MCP tools for trust scoring, Guard, Passport, Vault, Workflows, Compliance (OWASP/EU AI Act/NIST/ISO 42001), Cedar policies + ABAC attributes, SRE, context governance, and content provenance (EU AI Act Art. 50). Works with Claude Desktop, Cursor, and any MCP client. (approve_jit_grant and issue_jit_token are deliberately not exposed to the LLM — those actions live behind an authenticated session in the web UI.)
OpenClaw PluginTypeScriptopenclaw plugins install veriswarm11 tools + 5 hooks for OpenClaw agents. Local secret redaction, PII tokenization, policy enforcement, Session Sentry, audit. Per-feature enable/disable.
GitHub ActionPythonGitHub MarketplaceCI/CD trust gate — check agent trust scores in your pipeline
JSON SchemasJSONnpm install @veriswarm/schemasSchema definitions for events, profiles, scores, and workflows

Secret & PII protection at a glance

The packages share setting names but not behaviour. "Redacted locally" means replaced in-process, before any network call; "fails closed" lists what blocks (or withholds) instead of passing data through when a check can't run.

PackageSetting (default)Redacted locallySent to the VeriSwarm APIFails closed
Node SDKsecretsDetection (false)When on, guardOutboundText() redacts provider-prefix secrets (ghp_, sk-, AKIA, …). When off it is a no-op. Other methods are not filteredWhen on and a secret was found, the already-redacted text, for PII tokenization. Everything else you pass to a method is sent as-isguardOutboundText() returns the locally redacted text if tokenization fails
Python SDKsecrets_detection (False)Same as the Node SDK, via guard_outbound_text()Same as the Node SDKSame as the Node SDK
Python adapters (decorator, Claude Agent SDK, OpenAI Agents, CrewAI; LangChain handler)guard_secrets (True), guard_pii (True). The LangChain handler always guards secrets, does no PII tokenization, and enforces decisions only with enforce=TrueSecrets in string tool arguments (including strings nested in dict/list/tuple arguments), string tool output, error messages and audit eventsThe trust-decision check (tool name), and secret-redacted strings for PII tokenization; wrapped functions receive the tokenized arguments (strings, and strings inside dict/list/tuple arguments; other types pass unchanged)Anything but an explicit allow decision (including review and API errors) blocks the call; an input PII-tokenization failure blocks it; output that can't be tokenized, or a secret check that errors, is replaced with [VS:REDACTED:guard_unavailable]. on_deny="log" turns decision blocking off (a non-allow decision or decision-check error is logged and the call runs); a PII-tokenization outage still blocks
MCP Guard hooks (Claude Code)GUARD_SECRETS_DETECTION (off), GUARD_BLOCK_PROMPT_PII (on), GUARD_PII_FAIL_OPEN (off)Always: secrets in prompts (the prompt is blocked), MCP tool arguments and MCP tool responsesWith VERISWARM_API_KEY set: prompts (a prompt with a secret is blocked before this) and secret-redacted tool arguments/responses, for PII tokenization. With GUARD_SECRETS_DETECTION=1, tool-argument strings that contain a secret are sent unredacted first, for recoverable tokensSecret checks block. A tool-argument PII scan that can't finish blocks the call (unless GUARD_PII_FAIL_OPEN=1); a tool-response scan that can't finish withholds the output. The prompt PII check fails open with a warning
OpenClaw pluginsecretsDetection (false), piiEnabled (true), failOpen (false)Always: secrets in tool params and outbound messages (with secretsDetection on, these block / cancel instead). Tool results: secrets always, structured PII patterns when piiEnabledSecret-redacted param strings and message text, for PII tokenization and Session SentryPII tokenization, Session Sentry and hook errors block / cancel / withhold unless failOpen; missing secret rules always block. With secretsDetection off, another plugin's approval request can drop the param rewrite, so the tool itself may receive the secret
GitHub Actionfail-on-pii, fail-on-injection, fail-on-deny, fail-on-ci-exfil (all true)Nothing. Sensitive-named files (.env, keys, .git/) and files outside the workspace are skippedScanned file chunks (scan mode) and CI files/diffs (ci-exfil mode), as-isAn enabled gate fails on API errors or unexpected responses. The decision gate fails only on deny: a review decision passes CI, unlike the Python adapters

Quick Start

MCP Server (Recommended)

Add to your MCP client config (Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "veriswarm": {
      "command": "python3",
      "args": ["-m", "veriswarm_mcp"],
      "env": {
        "VERISWARM_API_URL": "https://api.veriswarm.ai",
        "VERISWARM_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Or use the setup CLI:

pip install veriswarm-mcp
veriswarm-setup --platform claude --api-key YOUR_API_KEY

This installs the MCP server, Guard hooks (PII protection + activity logging), and Guard Proxy config.

Python SDK

from veriswarm import VeriSwarmClient

client = VeriSwarmClient("https://api.veriswarm.ai", "YOUR_API_KEY")

# Register an agent
agent = client.register_agent({"slug": "my-agent", "display_name": "My Agent"})

# Check if an action should be allowed
result = client.check_decision(agent_id="agt_123", action_type="send_email")
print(result["decision"])  # "allow", "review", or "deny"

# Ingest events
client.ingest_event(
    event_id="evt_001", agent_id="agt_123", source_type="platform",
    event_type="task.completed", occurred_at="2026-04-01T00:00:00Z",
    payload={"task": "onboarding", "success": True}
)

Node.js SDK

import { VeriSwarmClient } from '@veriswarm/sdk'

const client = new VeriSwarmClient({
  baseUrl: 'https://api.veriswarm.ai',
  apiKey: 'YOUR_API_KEY'
})

const result = await client.checkDecision({
  agentId: 'agt_123',
  actionType: 'send_email'
})

OpenClaw Plugin

{
  plugins: {
    entries: {
      veriswarm: {
        enabled: true,
        config: {
          apiKey: "YOUR_API_KEY",
          piiEnabled: true,
          policyEnabled: true,
          injectionScan: true,
          auditEnabled: true
        }
      }
    }
  }
}

Free Plan

Get started with no credit card:

  • 5,000 trust score queries/day
  • Up to 10 agents
  • Unlimited event ingestion
  • Portable credentials issued on demand (rate-limited per plan; see pricing for current limits)

Sign up at veriswarm.ai.

Links

License

MIT

Reviews

No reviews yet

Be the first to review this server!