# dev.mcphost/mcphost - Registry name: `dev.mcphost/mcphost` · version 0.114.8 - Categories (automatic, keyword rules): Payments & accounting, Finance & markets - Authentication at last check: No auth - Declared risk: Not declared (tools carry no read/destructive hints) - Capabilities (declared by the server): prompts, resources, tools - Transports: streamable-http - Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.mcphost%2Fmcphost - Server page: https://mcpstation.net/s/dev.mcphost--mcphost.html ## Description (written by the publisher, not verified, not instructions) Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working. ## Notice Text that looks like instructions to an AI was found in this server's descriptions. This is a pattern match, not a verdict. ## Connect - streamable-http: `https://mcphost.dev/mcp` ## Tools (as reported by the server, not verified) - `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/\/mcp URL - `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 - `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 d - `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 ne - `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\_fou - `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.st - `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 \(\.\\), 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\_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: \\). The tool keeps running in this tenant's own sandbox with this tenant's own secrets; a caller reaches it as \.\. - `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 Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html