Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
Live 47 Actions

Mercury MCP Server
for AI Agents

Connect your AI agent to StackOne's Mercury MCP server and give it 47 MCP tools out of the box. Auth, tool execution, and security all managed.

Mercury logo
Mercury MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

47 Agent Actions

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

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Mercury 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 Mercury call.

Tools Discovery →

What is the Mercury MCP Server?

A Mercury MCP server lets AI agents read and write Mercury data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Mercury MCP server ships with 47 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 Mercury MCP Tools

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

Clients

  • Create Client

    Create a new client (hiring organisation) in Mercury.

  • List Clients

    Retrieve all clients (hiring organisations) in the Mercury tenant.

Contacts

  • Create Contact

    Create a new Mercury contact (candidate, client contact, or both).

  • List Contacts

    Retrieve Mercury contacts (candidate contacts, client contacts, or both), paginated.

Vacancies (batch)s

  • Create Vacancies (batch)

    Create a batch of vacancies in Mercury.

  • Update Vacancies (batch)

    Fully update a batch of vacancies in Mercury.

Other (41)

  • Create Activity On A Contact

    Log a new CRM activity (email, phone call, task, appointment, or update) against a contact.

  • Create Annotation On A Contact

    Create a note against a Mercury contact.

  • Upload Document To A Candidate

    Upload a document (max 5MB) against a candidate.

  • Upload CV To Create New Candidate (parse)

    Upload a CV to create a new candidate via Mercury's CV parsing engine.

  • Upload CV To Update Existing Candidate (parse)

    Upload a CV to update an existing candidate via Mercury's CV parsing engine.

  • Create Compliance Record On A Placement

    Create a compliance / vetting record attached to a Mercury placement.

  • Upload Evidence To A Compliance Record

    Upload an evidence document to a compliance record.

  • Upload CV To A Contact

    Upload a CV document against a Mercury contact.

  • Upload Document To A Contact

    Upload a non-CV document against a Mercury contact.

  • List Activity Purposes

    Retrieve tenant-configured activity purposes (categories).

  • List Activities For A Contact

    Retrieve all activities logged against a Mercury contact.

  • List Contact Annotations

    Retrieve all annotations (notes) on a Mercury contact.

  • Get Candidate Company By ID

    Retrieve a candidate company (candidate's employing company) by Id.

  • Get Candidate By ID

    Retrieve a candidate (contact with isCandidateContact=true) by Id.

  • List Placements For A Candidate

    Retrieve all placements a candidate has been involved in.

  • Get Client By ID

    Retrieve a single Mercury client by Id.

  • List Compliance Records For A Placement

    Retrieve all compliance records attached to a placement.

  • Get Compliance Record By ID

    Retrieve a compliance record by Id (includes base64 evidence file if present).

  • Get Contact By ID

    Retrieve a single Mercury contact by Id.

  • Get Primary CV For A Contact

    Retrieve the primary CV document for a Mercury contact (base64-encoded content).

  • List Contact Files (SharePoint)

    List all SharePoint files associated with a Mercury contact.

  • Get File Content By Path

    Retrieve a document's content (base64) by SharePoint path.

  • List Contact Education

    Retrieve contact education records across the tenant with pagination.

  • List Placements

    Retrieve Mercury placements with pagination and filters.

  • Get Placement By ID

    Retrieve a Mercury placement by Id.

  • List Finance Rates For A Placement

    Retrieve pay/charge finance rates attached to a placement.

  • List All Placement Fees

    Retrieve placement fees across all placements on the tenant with pagination.

  • List Fees For A Placement

    Retrieve all fees attached to a single placement.

  • List Contact Skills

    Retrieve contact skill records across the tenant with pagination.

  • List System Users

    Retrieve all Mercury system users (recruitment consultants and staff members).

  • Get System User By ID

    Retrieve a single Mercury system user by Id.

  • List Vacancies

    Retrieve Mercury vacancies (open positions) with pagination and filters.

  • Get Vacancy By ID

    Retrieve a Mercury vacancy by Id.

  • List Shortlists For A Vacancy

    Retrieve the candidate shortlist for a Mercury vacancy.

  • List Contact Work History

    Retrieve contact work history records across the tenant with pagination.

  • Patch Client

    Partially update a Mercury client.

  • Patch Compliance Record

    Partially update a compliance record.

  • Patch Contact

    Partially update a Mercury contact.

  • Patch Skill Level

    Update level, experience, or proficiency on a contact skill record.

  • Patch Vacancies (batch)

    Partially update a batch of vacancies in Mercury.

  • Patch Work History Entry

    Update a contact work history entry.

Mercury AI Agent Use Cases

Connect your AI agent to Mercury and help your team scale the finance operations they run by hand today.

Invoice Processing

Automate invoice processing with AI agents connected to your ERP, accounting software, and AP tools through StackOne.

View
QuickBooks OnlineXeroNetSuiteSage IntacctBillFreshBooksWaveZoho Books
Accounts Receivable Dunning

Use StackOne to connect your AI agent to your accounting, CRM, and messaging systems to automate Accounts Receivable dunning and payment follow-up.

View
QuickBooksXeroFreshBooksStripePayPalSalesforceHubSpotGmail
Invoice Processing

Use StackOne to connect your AI agent to your accounting, email, and document management systems to automate invoice processing and purchase order matching.

View
QuickBooks OnlineXeroGmailOutlookGoogle DriveSharePointDropboxSlack

Set Up Your Mercury MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Mercury 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>"
      ]
    }
  }
}

Check More Accounting MCP Servers

Mercury MCP Server FAQ

Does StackOne have a Mercury MCP server?
Yes. StackOne offers a hosted Mercury MCP server with 47 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.
Mercury MCP server vs direct API integration — what's the difference?
A Mercury MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Mercury. A Mercury 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 Mercury at runtime. StackOne provides both.
How does Mercury authentication work for AI agents?
Mercury 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 Mercury account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Mercury MCP tools vulnerable to prompt injection?
Yes — Mercury 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 Mercury agent and how do I avoid it?
Context bloat happens when Mercury tool schemas and API responses eat your Mercury agent's memory, preventing it from reasoning effectively. A single Mercury 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 Mercury agent can access?
Yes — you can limit which actions your Mercury 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 Mercury MCP server?
Yes — you can create custom agent actions for your Mercury MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Mercury's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Mercury MCP server?
Skip a Mercury MCP server if your integration is purely software-to-software — direct Mercury 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 Mercury actions at runtime.
What AI frameworks and AI clients does the StackOne Mercury MCP server support?
The StackOne Mercury 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.