Your agent asks to use a tool.
Should you let it?

MCP Server

Any agent. 3 lines of config.

{
  "mcpServers": {
    "veriswarm": {
      "command": "python",
      "args": ["-m", "src"],
      "env": {
        "VERISWARM_API_KEY": "vs_..."
      }
    }
  }
}

65+ tools for trust scoring, event reporting, security, identity, audit, and agent operations. Works with Claude Desktop, Cursor, and other MCP clients.

LangChain Adapter

Auto-instrument. 2 lines of code.

handler = VeriSwarmCallbackHandler(
    api_key="vs_...",
    agent_id="agt_..."
)
agent = initialize_agent(
    tools, llm,
    callbacks=[handler]
)

Every tool call, task completion, and error automatically reported. Optional enforcement mode can block denied actions automatically.

Portable Credentials

Agents carry proof of trust.

{
  "veriswarm": {
    "identity_score": 82,
    "risk_score": 15,
    "risk_band": "low",
    "policy_tier": "tier_2",
    "is_verified": true
  }
}

Signed JWT credentials agents present to any platform. Verify offline via the public JWKS endpoint with a short-lived token.

Trust Badges

Embed trust on any page.

<img src="https://api.veriswarm.ai
  /v1/badge/my-agent.svg
  ?style=compact&theme=dark"
/>

Server-rendered SVG badges showing real-time trust scores. Works in READMEs, docs, profile pages, and other places where images can load.

PII never reaches the LLM

Tokenize personal data before processing.

Names, emails, SSNs, phone numbers, medical records, credit cards — Guard detects and tokenizes PII using NER + regex before the LLM sees it. Agents work with tokens. Original data stays encrypted in the vault.

Block prompt injection in real time

Scan inputs and outputs for adversarial content.

Guard scans every user message and every tool response for injection patterns, persona shifts, delimiter attacks, and encoding tricks. Blocked attempts are logged in Vault and counted in the agent's trust score.

Enforce tool policies

Whitelist, blacklist, or require approval per tool.

Control which tools an agent can call, which parameters it can pass, and whether write actions require human approval. Policies are tenant-configurable and enforced transparently — the agent doesn't know the proxy is there.

Works with any MCP server

Cloud, Docker, or local. One URL change.

{
  "mcpServers": {
    "my-tools": {
      "command": "guard-proxy",
      "args": ["--target", "my-real-server"],
      "env": {
        "VERISWARM_API_KEY": "vs_..."
      }
    }
  }
}