Product: 1099Policy MCP

Your AI agent runs risk checks. Verifies coverage. Audits COIs.

1099Policy as a Model Context Protocol server. Claude, Cursor, ChatGPT, and any MCP-compatible client can call our tools through natural language. Connect once. Your agent stays in your stack.

Standardized tool surface

bindAssignment, issueCertificate, auditVendor, and checkCoverage. Typed inputs, structured outputs, MCP-compliant.

Any MCP client

Claude Desktop, Claude Code, Cursor, Continue, Cline, Zed, and any other MCP-compatible host. One config, every agent.

Scoped tokens + audit log

Per-tenant API keys with granular scopes. Every tool call is logged with agent identity, prompt context, and result.

Setup

Add 1099Policy to your agent in 30 seconds.

One command. The MCP server runs locally, brokers calls to the 1099Policy API, and presents tools to your client. No infrastructure to deploy, no daemon to maintain.

Configuration is per-client. Add the same server to Claude Desktop, Claude Code, Cursor, and any other MCP-compatible host.

Tool catalog

Every product capability, typed and discoverable.

The MCP server exposes 1099Policy's full surface: bind assignments, issue certificates, audit vendor COIs, check coverage by state, parse ACORD forms, list active policies, and pull audit trails.

Each tool ships with structured schemas, real examples, and rate-limit metadata.

Conversation flow

Natural language → coverage verified in seconds.

Does our HVAC sub in PA have active WC and GL for Saturday's install? becomes a typed tool call with the right contractor, work_state, and effective_date.

If the request is ambiguous, the tool returns a structured error your agent can reason over.

Multi-tenant safety

Scoped tokens. Every call audited.

Each MCP key is scoped to a tenant and a permission set: read-only audit, write to specific entities, or full account.

Every tool call logs the agent identity, prompt context, typed input, and structured result.

Trusted by

The teams that staff, dispatch, and pay contractors.

Which MCP clients does it work with?

Any MCP-compatible client, including Claude Desktop, Claude Code, Cursor, Continue, Cline, Zed, and local agent hosts.

What tools are exposed today?

Assignments, certificates, COI review, vendor audit, active policy lookup, and coverage verification tools are exposed with typed schemas.

How do tokens and authentication work?

Each MCP key is scoped to a tenant and permission set. Different clients can use different keys for the same account.

Can my agent actually bind real coverage?

Only when the token has write scope. Read-only audit keys can verify and inspect coverage without changing anything.

Where can I find the spec and source?

The setup guide and tool reference live in the 1099Policy docs.

Add 1099Policy to your agent in one command.

Generate a token, drop one line into your MCP config, and start asking your agent to issue COIs.

$claude mcp add 1099policy npx -y @1099policy/mcp-server⌘C to copy