Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery

Live 45 Actions

Candid Health MCP Server
for AI Agents

Connect your AI agent to StackOne's Candid Health MCP server and give it 45 MCP tools out of the box. Auth, tool execution, and security all managed.

Candid Health logo
Candid Health MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

45 Agent Actions

Create, read, update, and delete across Candid Health — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Candid Health MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Candid Health tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Candid Health call.

Tools Discovery →

What is the Candid Health MCP Server?

A Candid Health MCP server lets AI agents read and write Candid Health data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Candid Health MCP server ships with 45 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Candid Health MCP Tools

Every action from Candid Health's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Appointments

  • Create Appointment

    Create a pre-encounter appointment for a patient with scheduling and eligibility metadata.

  • Get Appointment

    Retrieve a single appointment by its Candid appointment ID.

  • Update Appointment

    Update an appointment using optimistic concurrency via the next version number.

Charge Captures

  • Create Charge Capture

    Create a charge capture holding pre-billing charge data before encounter submission.

  • List Charge Captures

    List charge captures filtered by patient, bundle, status, service dates, or provider.

  • Get Charge Capture

    Retrieve a single charge capture by its Candid charge capture ID.

  • Update Charge Capture

    Update charge capture data or bundle assignment before aggregation.

Coverages

  • Create Coverage

    Create an insurance coverage record for a patient with payer, plan, subscriber, and benefits data.

  • List Coverages

    List coverages filtered by patient, payer, and status with cursor pagination.

  • Get Coverage

    Retrieve a single coverage record by its Candid coverage ID.

  • Update Coverage

    Update a coverage record using optimistic concurrency via the next version number.

Diagnosis

  • Create Diagnosis

    Attach an ICD diagnosis code to an existing encounter.

  • Update Diagnosis

    Update an existing diagnosis code, code type, name, or POA indicator.

Encounters

  • Create Encounter

    Create a professional encounter (claim) with patient, providers, diagnoses, and service lines.

  • List Encounters

    List professional encounters filtered by status, dates, patient, provider, payer, and more.

  • Get Encounter

    Retrieve a single encounter (claim) with its providers, diagnoses, and service lines.

  • Update Encounter

    Update fields on an existing encounter (claim), including status, providers, and billing metadata.

Insurance Refunds

  • Create Insurance Refund

    Post an insurance refund with allocations to service lines, claims, or billing provider unattributed cash.

  • List Insurance Refunds

    List insurance refunds filtered by payer, service line, claim, or billing provider.

  • Get Insurance Refund

    Retrieve a single insurance refund and its allocations by refund ID.

  • Update Insurance Refund

    Update an insurance refund's amount, timestamp, notes, or allocations.

Patients

  • Create Patient

    Create a pre-encounter patient with demographics, contacts, guarantors, and other administrative data.

  • Search Patients

    Search patients by MRN or other identifier fields.

  • List Patients

    List patients with cursor pagination, sort, filters, and free-text search.

  • Get Patient

    Retrieve a single patient by their Candid patient ID.

  • Update Patient

    Update a patient record using optimistic concurrency via the next version number.

Payers

  • Get Payer

    Retrieve a single payer from Candid's canonical payer list by its UUID.

  • List Payers

    List all payers on Candid's canonical payer list with optional name search.

Service Lines

  • Create Service Line

    Add a service line (CPT/HCPCS code) with charges and diagnosis pointers to an encounter.

  • Update Service Line

    Update an existing service line's code, modifiers, units, charge, or diagnosis pointers.

  • Delete Service Line

    Remove a service line from its encounter by service line ID.

Tasks

  • Create Task

    Create a billing operations task tied to an encounter with type, category, and assignee.

  • List Tasks

    List billing operations tasks filtered by status, category, assignee, or encounter.

  • Get Task

    Retrieve a single task with its notes, status history, and encounter reference.

  • Update Task

    Update a task's status, assignee, notes, or blocking reasons.

Write-Offs

  • Create Write-Offs

    Post one or more write-offs applied to a service line, claim, or billing provider.

  • List Write-Offs

    List write-offs filtered by payer, claim, service line, billing provider, or account type.

  • Get Write-Off

    Retrieve a single write-off record by its Candid write-off ID.

Other (7)

  • List Visits

    List appointment visits within a date range with pagination and sorting.

  • Get Claim Exports

    Fetch CSV export files of claim version changes within a date window.

  • Get Insurance Adjudication

    Retrieve a single insurance adjudication (ERA/EOB posting) by its Candid ID.

  • Run Eligibility Check

    Submit a real-time 270/271 eligibility check to a payer via Stedi.

  • Submit Eligibility Batch

    Submit a batch of eligibility checks to payers for asynchronous processing.

  • Deactivate Patient

    Deactivate (soft-delete) a patient using optimistic concurrency via the next version number.

  • Revert Write-Off

    Reverse a previously posted write-off, restoring the balance on its target.

Set Up Your Candid Health MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Candid Health in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Candid Health MCP Server FAQ

Does StackOne have a Candid Health MCP server?
Yes. StackOne offers a hosted Candid Health MCP server with 45 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Candid Health MCP server vs direct API integration — what's the difference?
A Candid Health MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Candid Health. A Candid Health MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Candid Health at runtime. StackOne provides both.
How does Candid Health authentication work for AI agents?
Candid Health authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Candid Health account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Candid Health MCP tools vulnerable to prompt injection?
Yes — Candid Health MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Candid Health agent and how do I avoid it?
Context bloat happens when Candid Health tool schemas and API responses eat your Candid Health agent's memory, preventing it from reasoning effectively. A single Candid Health query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Candid Health agent can access?
Yes — you can limit which actions your Candid Health agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Candid Health MCP server?
Yes — you can create custom agent actions for your Candid Health MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Candid Health's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Candid Health MCP server?
Skip a Candid Health MCP server if your integration is purely software-to-software — direct Candid Health API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Candid Health actions at runtime.
What AI frameworks and AI clients does the StackOne Candid Health MCP server support?
The StackOne Candid Health MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.