# Mcphost

> Mcphost is a freemium MCP server for cloud and infrastructure. Hosted MCP runtime where an agent publishes its own tools and schedules them. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $19 a month
- **Platforms:** API, Web
- **Website:** https://mcphost.dev
- **Repository:** https://github.com/j0yen/mcphost
- **MCP Registry name:** dev.mcphost/mcphost
- **Categories:** cloud and infrastructure, developer tools
- **Listing updated:** 2026-11-14

## About

The odd part of this server is that the tools are written by your agent, not by the vendor. During a task the agent calls tool_publish with some source, the schema is inferred, and the new tool is live without a restart. It can then attach a schedule so it fires overnight while you sleep, and you read its log in the morning.

Anything it builds is meant to outlive the chat: published tools, stored secrets and kept state. Calls past a plan limit fail with a quota_exceeded error that reports the limit and your usage.

The first call creates a tenant and returns a private URL, with no form or card. The page says the source is open under MIT OR Apache-2.0 and that the sandbox is on by default.

## Features

- **Publish by tool call:** The agent writes and publishes a tool mid-task.
- **Scheduled triggers:** A published tool can fire on a schedule.
- **Logs and history:** Tool logs, version history and diffs are available.
- **Rollback:** A previous version of a tool can be restored.
- **Stored secrets and state:** Secrets and state persist beyond the conversation.
- **Sandbox on by default:** Published code runs in a sandbox.

## Good for

- Let an agent keep a recurring check running overnight
- Turn a one-off script into a reusable tool
- Review what a scheduled tool did via its log
- Roll back a tool change that broke a workflow

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcphost https://mcphost.dev/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcphost.dev/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcphost": {
      "url": "https://mcphost.dev/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcphost": {
      "type": "http",
      "url": "https://mcphost.dev/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcphost": {
      "serverUrl": "https://mcphost.dev/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcphost": {
      "type": "http",
      "url": "https://mcphost.dev/mcp"
    }
  }
}
```

## Tools

- `signup`: Explicit signup, for a client that cannot keep a session across calls: create a tenant and receive a bearer key and namespace. Unauthenticated. Most clients never need this -- any other host.*/billing.* call from a fresh connection creates a tenant implicitly and returns its own /u/<secret>/mcp URL in the response's onboarding field. Recommended here: pass handoff: true to receive a short-lived, s
- `host.quickstart`: Return the shortest ordered sequence of calls to a working tool of `kind`, with your namespace and a filled-in example already substituted in, plus the current limits and a try_before_call table naming the one dry-run tool for each case. Read-only -- this call alone never creates a tenant. Call this before host.tool_publish if you're not sure what a spec should look like. Unauthenticated callers g
- `host.help.search`: Search this host's own documentation and tool descriptions. Returns up to k hits (default 3, response under 2 KB), each with a snippet, the nearest runnable example and an anchor. Read-only, anonymous, no tenant data -- call it with the error text or import line you are stuck on before reading any docs file.
- `host.help.get`: Return the documentation section an anchor points at: its text (at most 4 KB) and its first fenced example. Pass an anchor exactly as an error, hint or help entry printed it, e.g. a rate_limited error's `anchor`. Read-only, anonymous, no tenant data. An unknown anchor is anchor_not_found with the nearest anchors in did_you_mean.
- `host.errors`: List every error code this host can return, each with its class (agent_fault | host_refusal | upstream_fault | plan_limit | host_fault), family, remedy, docs anchor, retryable flag and help_url -- the same object GET /errors.json serves. Pass code to get one row; a misspelt code answers tool_not_found with did_you_mean. Read-only, anonymous, no tenant data.
- `host.redeem`: Exchange a signup(handoff: true) handoff_token for the tenant key it was issued for. Single-use: a second redemption fails with handoff_token_redeemed; past its expiry it fails with handoff_token_expired. Unauthenticated -- the token itself is the proof.
- `billing.plans`: The plan catalog (price and quotas per plan) and whether Stripe billing is configured on this host. Anonymous callers get the same answer as tenants.
- `host.whoami`: Return the calling tenant's identity, including key_age_s and key_rotated_at for auditing credential hygiene.
- `host.tool_publish`: Publish a tool of a registered kind (e.g. python, http or echo; the kind argument's enum lists them all) under this tenant's namespace. Call host.quickstart(kind) first for a filled-in example spec and the full publish-to-call sequence. Python's sandbox API: import mcphost (mcphost.table, mcphost.state, mcphost.docs). Name must match ^[a-z][a-z0-9_]{1,40}$; a rejection names the failing field and 
- `host.tool_call`: Invoke a tool this tenant has already published, by its local name -- the same real, metered call as calling it directly by its namespaced name (<namespace>.<name>), for a session that has no way to see its own namespaced tool name yet. Unlike host.tool_test, this counts toward host.usage and appears in host.tool_logs. Pass async: true for a tool that needs more than the call deadline: returns {ru
- `host.tool_test`: Dry-run a published tool by name: verdict (pass/will_fail/unverifiable), writes rolled back (dry_run); see host.quickstart.
- `host.state.set`: Write one key in this tenant's key-value state namespace; value may be any JSON value. Overrun of the plan's state_bytes_max quota fails with state_quota_exceeded and writes nothing.
- `host.state.get`: Read one key from this tenant's key-value state namespace. Returns found: false (not an error) if the key was never set.
- `host.state.list`: List keys (with their current values) in this tenant's key-value state namespace, optionally filtered by prefix.
- `host.tool_share`: Share one of this tenant's published tools with everyone (visibility: "public") or with a named group this tenant owns (visibility: "group", group: <name>). The tool keeps running in this tenant's own sandbox with this tenant's own secrets; a caller reaches it as <this tenant's namespace>.<name>.
- `host.feedback.send`: Tell the host's humans what you needed: kind, up to 2048 bytes of text, optional context. Works before signup. Returns feedback_id.
- `host.feedback.list`: List your own feedback (newest first, status received). Anonymous callers get [].
- `host.resume`: Resume where you left off in one call (at most 4096 bytes): your tools with each one's last call status, unfinished runs, your newest notes, what changed on the host since your last call, and one suggested next_call. truncated names any section that was cut -- call that section's own tool (host.tool.list, host.runs.list, host.note.list, host.changelog) for the rest. Read-only. An unauthenticated c

## FAQ

### How much does it cost?

The free plan has 500 calls a day per tenant and needs no card; Pro is $19 a month with 50,000 calls included, then $0.001 a call.

### Is the source available?

The page says it is open under MIT OR Apache-2.0.

### Which clients work?

Claude Code, Codex CLI, Cursor, Claude.ai and any client that speaks MCP over streamable HTTP.

### What happens at the limit?

A call past the daily or monthly limit fails with quota_exceeded.

### Is Mcphost free?

Mcphost has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

### How do I add Mcphost to Claude Code?

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

### What are the best alternatives to Mcphost?

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

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/mcphost
