Connect
Optimize
Secure
Live 30 Actions
Logfire MCP Server
for AI Agents
Connect your AI agent to StackOne's Logfire MCP server and give it 30 MCP tools out of the box. Auth, tool execution, and security all managed.
Logfire MCP Server
Built by 
StackOne
StackOne 
Coverage
30 Agent Actions
Create, read, update, and delete across Logfire — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Logfire MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Logfire 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 Logfire call.
Tools Discovery →What is the Logfire MCP Server?
A Logfire MCP server lets AI agents read and write Logfire data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Logfire MCP server ships with 30 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 Logfire MCP Tools
Every action from Logfire's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Projects
- Create Project
Create a new project
- List Projects
List all projects accessible to the authenticated user
- Update Project
Update an existing project
- Delete Project
Delete a project
Project Infos
- Get Project Info
Get details of a specific project
Organizations
- Create Organization
Create an organization owned by the token's user (on-prem only).
- List Organizations
List all organizations (self-hosted admin only).
- Get Organization
Read an organization by id (self-hosted admin only).
- Update Organization
Update an organization (self-hosted admin only).
- Delete Organization
Delete an organization (self-hosted admin only).
Self Hosted Organization Invitations
- Create Self Hosted Organization Invitation
Create a single-use organization invitation and return its join URL (self-hosted admin only).
Alerts
- Create Alert
Create a new alert.
- List Alerts
List all alerts for a project.
- Get Alert
Get an alert.
- Update Alert
Update an alert.
- Delete Alert
Delete an alert.
Channels
- Create Channel
Create a notification channel.
- List Channels
List all notification channels for the organization the project belongs to.
- Get Channel
Get a single notification channel by ID
- Update Channel
Update a notification channel.
- Delete Channel
Delete a notification channel.
Dashboards
- Create Dashboard
Create Dashboard
- List Dashboards
List Dashboards
- Get Dashboard
Get Dashboard
- Update Dashboard
Update Dashboard
- Delete Dashboard
Delete Dashboard
Variables Configs
- Get Variables Config
Get the full variables configuration for a project.
Variables
- Create Variable
Create a new variable definition, optionally with labels and versions.
- Update Variable
Update an existing variable definition, optionally with labels and versions.
Variable By Names
- Get Variable By Name
Get a variable definition by name with current labels and latest version.
Set Up Your Logfire MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Logfire in under 10 lines of code.
Agent Frameworks
JSON{
"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
Logfire MCP Server FAQ
Does StackOne have a Logfire MCP server?
Yes. StackOne offers a hosted Logfire MCP server with 30 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.
Logfire MCP server vs direct API integration — what's the difference?
A Logfire MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Logfire. A Logfire 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 Logfire at runtime. StackOne provides both.
How does Logfire authentication work for AI agents?
Logfire 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 Logfire account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Logfire MCP tools vulnerable to prompt injection?
Yes — Logfire 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 Logfire agent and how do I avoid it?
Context bloat happens when Logfire tool schemas and API responses eat your Logfire agent's memory, preventing it from reasoning effectively. A single Logfire 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 Logfire agent can access?
Yes — you can limit which actions your Logfire 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 Logfire MCP server?
Yes — you can create custom agent actions for your Logfire MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Logfire's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Logfire MCP server?
Skip a Logfire MCP server if your integration is purely software-to-software — direct Logfire 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 Logfire actions at runtime.
What AI frameworks and AI clients does the StackOne Logfire MCP server support?
The StackOne Logfire 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.