Live 83 Actions

Harness FME MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Harness FME MCP server support?

The StackOne Harness FME 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.

Connect your AI agent to StackOne's Harness FME MCP server and give it 83 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Harness FME MCP Server

Built by

StackOne

Coverage

83 Agent Actions

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

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Harness FME 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 Harness FME call.

Tools Discovery →

What is the Harness FME MCP Server?

A Harness FME MCP server lets AI agents read and write Harness FME data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Harness FME MCP server ships with 83 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 Harness FME MCP Tools

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

Environments

Create Environments
Create an FME environment in a project.
Get Environments
List the FME environments in a project.
Update Environments
Update an FME environment with JSON Patch.
Delete Environments
Delete an FME environment from a project.

Traffic Types

Create Traffic Types
Create a traffic type in a project.
Get Traffic Types
List the traffic types defined in a project.
Delete Traffic Types
Delete a traffic type by its ID.

Feature Flags

Create Feature Flag
Create a feature flag for a traffic type in a project.
Get Feature Flag
Get the metadata of one feature flag in a project.
List Feature Flags
List feature flag metadata in a project.
Update Feature Flag
Update a feature flag description, tags or rollout status with JSON Patch.

Feature Flag Definition In Environments

Create Feature Flag Definition In Environment
Configure a feature flag in an environment with treatments and rules.
Get Feature Flag Definition In Environment
Get the definition of a feature flag in one environment.

Segments

Create Segment
Create a segment for a traffic type in a project.
List Segments
List the segments in a project.
Delete Segment
Delete a segment from a project.

Rule-Based Segments

Create Rule-Based Segment
Create a rule-based segment for a traffic type in a project.
List Rule-Based Segments
List the rule-based segments in a project.
Delete Rule-Based Segment
Delete a rule-based segment from a project.

Large Segments

Create Large Segment
Create a large segment for a traffic type in a project.
List Large Segments
List the large segments in a project.

Change Requests

Get Change Request
Get an open change request by its ID.
List Change Requests
List change requests in a project or environment.

Flag Sets

Create Flag Set
Create a flag set in a project.
Get Flag Set
Get a flag set by its ID.
List Flag Sets
List the flag sets in a project.
Delete Flag Set
Delete a flag set by its ID.

Attributes

Get Attributes
List the attribute schemas of a traffic type.
Update Attribute
Partially update an attribute schema.
Delete Attribute
Delete an attribute schema from a traffic type.

Aggregated Users

Get Aggregated Users
List Harness users with their role assignments in an account, org or project.
Get Aggregated User
Get one Harness user with their role assignments.

Users

Add Users
Invite users by email to an account, org or project.
Remove User
Remove a user from an account, org or project scope.

User Groups

Get User Group
Get one Harness user group by identifier.
Delete User Group
Delete a Harness user group.

Other (47)

Create Large Segment Definition For Environment
Enable a large segment in an environment.
Create Change Request For Rule-Based Segment
Submit a change to a rule-based segment for approval.
Add User To User Groups
Set the user groups a user belongs to.
Get Projects (Workspaces)
List FME projects (formerly workspaces) in the account.
List Feature Flag Definitions In Environment
List the feature flag definitions configured in an environment.
Get Segment Keys In Environment
List the keys of a segment in an environment.
List Segments In Environment
List the segments enabled in an environment.
List Rule-Based Segments In Environment
List the rule-based segments enabled in an environment.
Get Rule-Based Segment By Name
Get a rule-based segment in a project by its name.
Get Large Segment In Project (Workspace) By Name
Get a large segment in a project by its name.
List Large Segments In Environment
List the large segments enabled in an environment.
Get Rollout Statuses
List the rollout statuses available in a project.
Get User Group List
List Harness user groups in an account, org or project.
Get Project List
List the Harness projects the caller is a member of.
Get Organization List
List Harness organizations in the account.
Get Pending Users Aggregated
List users with pending invites in an account, org or project.
Update Feature Flag Description
Replace the description of a feature flag.
Update Segment Keys In Environment Via JSON
Add keys to a segment in an environment from a JSON list.
Update Rule-Based Segment Definition
Update the rules and exclusions of a rule-based segment in an environment.
Update Change Request Status
Approve, reject or withdraw an open change request.
Update User Info
Update a Harness user profile.
Delete A Feature Flag
Delete a feature flag from a project.
Remove Feature Flag Definition From Environment
Remove a feature flag definition from an environment.
Remove Segment Keys From Environment
Remove a list of keys from a segment in an environment.
Delete Rule-Based Segment In Environment
Remove a rule-based segment from an environment.
Delete Large Segment In Project (Workspace)
Delete a large segment from a project.
Delete Large Segment In Environment
Remove a large segment from an environment.
Delete Project
Delete a Harness project and its FME project.
Delete Invite
Delete a pending user invite.
Archive A Feature Flag
Archive a feature flag so it is no longer active for regular use.
Unarchive A Feature Flag
Restore an archived feature flag so it becomes active again.
Full Update Feature Flag Definition In Environment
Replace the whole definition of a feature flag in an environment.
Kill Feature Flag In Environment
Kill a feature flag in an environment so every key gets the default treatment.
Partial Update Feature Flag Definition In Environment
Update fields of a feature flag definition in an environment with JSON Patch.
Reallocate Traffic (Reseed Bucketing)
Reseed the bucketing of a feature flag in an environment.
Restore Feature Flag In Environment
Restore a killed feature flag in an environment.
Deactivate Segment In Environment
Deactivate a segment in an environment.
Enable Segment In Environment
Enable an existing segment in an environment.
Enable Rule-Based Segment In Environment
Enable a rule-based segment in an environment.
Submit Change Request
Submit a change to a feature flag or segment for approval.
Associate Tags
Set the tags on a feature flag.
Bulk Upload Attribute Via JSON
Create or replace many attribute schemas at once from JSON.
Save Attribute
Create or overwrite an attribute schema for a traffic type.
Post User Group
Create a Harness user group.
Put User Group
Update a Harness user group.
Post Project
Create a Harness project, which also creates its FME project (workspace).
Put Project
Update a Harness project.

Set Up Your Harness FME MCP Server in Minutes

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

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What Hundreds of Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.

14 min read

Harness FME MCP Server FAQ

Does StackOne have a Harness FME MCP server?

Yes. StackOne offers a hosted Harness FME MCP server with 83 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.

Harness FME MCP server vs direct API integration — what's the difference?

A Harness FME MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Harness FME. A Harness FME 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 Harness FME at runtime. StackOne provides both.

How does Harness FME authentication work for AI agents?

Harness FME 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 Harness FME account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Harness FME MCP tools vulnerable to prompt injection?

Yes — Harness FME 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 Harness FME agent and how do I avoid it?

Context bloat happens when Harness FME tool schemas and API responses eat your Harness FME agent's memory, preventing it from reasoning effectively. A single Harness FME 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 Harness FME agent can access?

Yes — you can limit which actions your Harness FME 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 Harness FME MCP server?

Yes — you can create custom agent actions for your Harness FME MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Harness FME's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Harness FME MCP server?

Skip a Harness FME MCP server if your integration is purely software-to-software — direct Harness FME 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 Harness FME actions at runtime.

What AI frameworks and AI clients does the StackOne Harness FME MCP server support?

The StackOne Harness FME 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.

Start Free Book Demo

Harness FME MCP Serverfor AI Agents