Skip to content
MCP server

Hydrant

Issue, project and dependency tracker your own AI agent can read and update over MCP

Install
Pricing
Freemium
Platforms
Web, API
Runs
Remotely
Version
1.0.2
Listing updated
2 days ago

About Hydrant

Hydrant is a freemium MCP server for productivity. It runs as a hosted remote server, so there is nothing to install locally.

Hydrant does not run agents or supply a model. You bring a client such as Claude Code, Claude or Codex, approve it once in the browser, and it gets one workspace and a named place in the history. The agent never gets more than the role of the person who approved it.

The hosted server can read workspace context and, where access allows, create and update issues, add comments and manage relationships. A first call to get_workspace_identity confirms which workspace the agent landed in. Sign-in uses OAuth, so no static API key is needed, and access can be revoked under Settings, then Agents.

A companion repository of agent skills covers the ticket lifecycle: capture, refine, prep, go, review triage and ship. Each issue carries an Agent Work Record showing who let the agent in and who signed off the work.

Install

Run in a terminal

claude mcp add --transport http hydrant https://hydrant.dev/api/mcp

Add to Settings → Connectors → Add custom connector

https://hydrant.dev/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "hydrant": {
      "url": "https://hydrant.dev/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "hydrant": {
      "type": "http",
      "url": "https://hydrant.dev/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "hydrant": {
      "serverUrl": "https://hydrant.dev/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "hydrant": {
      "type": "http",
      "url": "https://hydrant.dev/api/mcp"
    }
  }
}

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

get_workspace_identity
Returns the name and ID of the connected workspace.

What it does

Workspace-scoped access
The agent works in one approved workspace and never exceeds your role.
Issue and relationship tools
Read context, create and update issues, comment and link blockers.
Browser OAuth sign-in
Approve the connection in the browser instead of pasting an API key.
Agent Work Record
Each issue records who admitted the agent and who accepted the result.
Optional workflow skills
A public skills pack guides capture, refinement, building and review.

Good for

  • Let a coding agent file and refine issues from bug reports
  • Ask an agent for open issues and their blockers
  • Have an agent summarize activity on a given issue
  • Track which agent changed what, with a named history

Pricing

Freemium, from $5 a month

Free plan; Solo Pro $60/year ($5/month); Team $120 per human per year

Prices change. Check hydrant.dev before you buy.

Hydrant FAQ

Does Hydrant provide the AI model?

No. You connect your own MCP client; Hydrant only supplies the workspace.

Which clients are tested?

Claude Code, Claude (claude.ai or Desktop) and Codex; Codex needs version 0.154.0 or newer.

Do agents cost extra?

No. Agents never take a seat; the Free plan allows 2 agent connections per workspace and Solo Pro allows 20.

Can I export my data?

Owners and admins can export a whole workspace as JSON and Markdown on any plan.

Is Hydrant free?

Hydrant has a free plan, with paid plans for more usage or features. Paid plans start at $5 a month.

How do I add Hydrant to Claude Code?

Run this command in your terminal: claude mcp add --transport http hydrant https://hydrant.dev/api/mcp

What are the best alternatives to Hydrant?

The closest alternatives to Hydrant are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Hydrant

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ha MCP

    MCP server

    MCP server for managing and automating Home Assistant from AI assistants

    Runs locally
    • 8 tools
    • Open source
    • 7.9K GitHub stars
    • Productivity