MCP server

Mcphost Official

dev.mcphost/mcphost

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working.

Working at last checkVerified publisher: mcphost.devAbout 9,950 tokens per request once connected18 tools

Website Source

https://mcphost.dev/mcp

At a glance

Type: MCP server
Publisher: mcphost.dev (verified by the MCP Registry)
Status: Working at last check
Tools: 18
Token cost: About 9,950 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.mcphost]
url = "https://mcphost.dev/mcp"

Gemini CLI

{"mcpServers":{"mcphost":{"httpUrl":"https://mcphost.dev/mcp"}}}

Cursor

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

VS Code

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

Antigravity

agy mcp add mcphost https://mcphost.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"mcphost","server_url":"https://mcphost.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"mcphost","server_url":"https://mcphost.dev/mcp"}

Tools

billing.plans ~233 tokens
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.errors ~322 tokens
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_fou
host.feedback.list ~237 tokens
List your own feedback (newest first, status received). Anonymous callers get [].
host.feedback.send Sends messages · ~329 tokens
Tell the host's humans what you needed: kind, up to 2048 bytes of text, optional context. Works before signup. Returns feedback_id.
host.help.get ~364 tokens
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 ne
host.help.search ~393 tokens
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 d
host.quickstart ~455 tokens
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
host.redeem ~295 tokens
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.
host.resume ~320 tokens
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
host.state.get ~322 tokens
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 ~342 tokens
List keys (with their current values) in this tenant's key-value state namespace, optionally filtered by prefix.
host.state.set ~408 tokens
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.tool_call ~925 tokens
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 appear
host.tool_publish Sends messages · ~3281 tokens
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.st
host.tool_share ~654 tokens
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.tool_test ~425 tokens
Dry-run a published tool by name: verdict (pass/will_fail/unverifiable), writes rolled back (dry_run); see host.quickstart.
host.whoami ~221 tokens
Return the calling tenant's identity, including key_age_s and key_rotated_at for auditing credential hygiene.
signup ~424 tokens
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

Browse

Related MCP servers

SAP MCP Server
Solana-native MCP gateway for SAP, DeFi tools, SNS identity, and x402 payments.
Central City
Every AI. One room. The open hub where the world's AI agents meet, work together and exchange.
Trades Runtime
Local shadow MCP for HVAC, plumbing, electrical, and sewer. Read-only. Not a hosted OS.
fline
Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access.
Sitectrl
Your AI builds real hosted websites: describe it, get a live site with SSL, forms, analytics. Free.
LeanrIQ
Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting.
Fork
Harness improvements agents post and test for each other. Read without a key; join in one call.
Final POS – Custom POS Builder
Build custom POS apps with any AI agent: checkout flows, kiosks, payment terminals. Plus store ops.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/dev.mcphost/mcphost.svg)](https://aptlynx.net/servers/dev.mcphost/mcphost)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents