Overview - Cotality developer portal

Welcome to the Cotality MCP — a unified MCP server for accessing Cotality’s property data, analytics, and risk intelligence. Connect once, discover available tools automatically, and integrate property insights directly into your AI agents and workflows.

What is MCP?

The Model context protocol (MCP) is an open standard that defines how AI agents and LLM-powered applications discover and call external tools at runtime. Instead of building custom API integrations for each data source, an MCP client connects to an MCP server, receives a list of available tools with their schemas, and invokes them using a standard JSON-RPC interface. This means your AI agent can dynamically discover what data is available and call the right tools without any hardcoded API logic.

How Cotality MCP works

Cotality MCP is a single MCP endpoint. When you connect, it returns the tools available under your access token’s scopes. You can then call any of those tools through the same connection to access all the Cotality property data and analytics tools your license includes.

Transport: HTTP streaming

Cotality MCP uses HTTP streaming as its MCP transport. Your client opens a streaming HTTP connection to the MCP endpoint, and all MCP communication — tool discovery, tool calls, and responses — flows over that connection. Most common MCP client libraries (e.g., MCP Python SDK) handle the transport automatically. You provide the endpoint URL and authentication, and the library manages the connection lifecycle.

Session lifecycle

Connect — Your MCP client opens a streaming HTTP connection to the MCP endpoint with your bearer token.
Initialize — The client and server exchange capabilities. The MCP server confirms which protocol features are supported.
Discover tools — The client calls tools/list to receive the tools available under your scopes, including their names, descriptions, and input/output schemas.
Discover prompts and resources (optional) — The client calls prompts/list and resources/list to receive the reusable prompt templates and reference documents. Unlike tools, these are not scope-filtered. See Property data prompts and resources and Market and trend analytics prompts and resources.
Call tools — The client calls tools/call with a tool name and input parameters. The server executes the tool and returns the result.
Disconnect — The client closes the connection when done.

If the connection drops, re-establish it and start from step 1. There is no server-side session state to recover.

Steps 3 and 4 are cheap and worth doing every session. Discovery is the only reliable way to know what your token can reach — scopes change when your entitlements are updated.

Tool naming

Cotality MCP is a single endpoint that aggregates several backend servers. Each tool name carries a short server prefix so names stay unique across them:

clip-find_property_by_clip
└──┘ └──────────────────┘
 │            └── tool name
 └── server prefix

Prefix	Server	Tools
`clip-`	CLIP resolution	`clip-find_property_by_clip`

Always use the full prefixed name in tools/call. The unprefixed name is the server’s internal registration and is not callable through the Cotality MCP endpoint.

Treat tools/list as the source of truth for exact names rather than hardcoding them. The prefix is applied by the gateway, so it is always present in what you receive.

Key concepts

Concept	Description
MCP	Model context protocol — an open standard for enabling AI agents and applications to dynamically discover and invoke external tools at runtime. Defines how clients and servers communicate tool schemas and execute tool calls in a consistent, interoperable way.
HTTP streaming	The transport mechanism used by the MCP server. Instead of sending individual HTTP requests for each operation, the client opens a persistent streaming connection. All MCP messages — including tool discovery and tool calls — are exchanged over this single connection, enabling real-time, bidirectional communication.
JSON-RPC	The protocol used for encoding requests and responses between the client and the MCP server. It is a lightweight, stateless remote procedure call protocol that uses JSON for message formatting. Each tool call and response follows the JSON-RPC specification.
Tool	A callable function exposed by the MCP server (e.g., `clip-find_property_by_clip`). Each tool has a defined input schema and returns structured JSON.
Prompt	A reusable, parameterized template that produces a well-formed instruction for a model. Discovered with `prompts/list`. See Property data prompts and resources and Market and trend analytics prompts and resources.
Resource	A read-only reference document the model can load as context, addressed by URI. Discovered with `resources/list`.
CLIP	Cotality’s unique, persistent numeric identifier for a US property parcel. Most data tools take a CLIP as input, so resolve an address to a CLIP first. See CLIP tools.
Scopes	Your access token determines which tools are available. Calling `tools/list` returns only the tools your token is authorized to use.

Next steps

Authentication — Get your access token
MCP inspector — Make your first tool call
Tool catalog — Browse all available tools by domain
Property data prompts and resources — Use the built-in prompt templates and reference documents for CLIP, characteristics, and climate risk
Market and trend analytics prompts and resources — Use the built-in prompt templates and reference documents for analytics
MCP tool errors — Handle failures and the retryable flag
Connect an MCP client — Set up VS Code, Cursor, Claude Code, or Windsurf
Python example — Programmatic integration with the MCP Python SDK

The full integration guides (client setup, Python SDK, and the interactive tester) live in the Guides tab for easy reference alongside prompting patterns and developer resources.

​What is MCP?

​How Cotality MCP works

​Transport: HTTP streaming

​Session lifecycle

​Tool naming

​Key concepts

​Next steps

What is MCP?

How Cotality MCP works

Transport: HTTP streaming

Session lifecycle

Tool naming

Key concepts

Next steps