mcphost
Description
Host your MCP tool over streamable HTTP in one command.
What our measurements say
mcphost is a remote MCP server published at mcphost.dev. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 1,027 ms, a delay an agent will notice. It exposes a broad tool surface of 49 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names are descriptive and indicate their purpose (e.g., 'host.tool_publish', 'host.tool_remove').
- Parameters are well-defined with clear types and required/optional status.
Weaknesses
- Some descriptions lack explicit usage scenarios (e.g., 'host.whoami' only states purpose, not when to use it).
- Parameter 'spec' in 'host.tool_publish' is an object but lacks schema details.
- Potential overlap between 'host.tool_test' and 'host.tool_call' in tool invocation contexts.
host.tool_publish— Parameter 'spec' is an object but lacks schema definition.host.whoami— Description does not explain when to use the tool.host.tool_test— Overlaps with 'host.tool_call' in invocation context ambiguity.
Verdict
Event narrative
Sign up free to generateRaw observations
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 38ms → warm 39ms (penalty 0ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
signupCreate a tenant and receive a bearer key and namespace. Unauthenticated.
namestringrequired
host.whoamiReturn the calling tenant's identity.
tenant_keystring
host.tool_publishPublish a tool of a registered kind (chain, echo, http, python) under this tenant's namespace. Call host.quickstart(kind) first for a filled-in example spec and the full publish-to-call sequence. Name must match ^[a-z][a-z0-9_]{1,40}$; a rejection names the failing field and a corrected example. Try host.tool_test before a real call.
kindstringrequirednamestringrequiredspecobjectrequiredtenant_keystring
host.quickstartReturn 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. Call this before host.tool_publish if you're not sure what a spec should look like. Unauthenticated callers get the signup step first.
kindstringrequiredtenant_keystring
host.tool_listList this tenant's published tools.
tenant_keystring
host.tool_removeRemove a published tool by its local name.
namestringrequiredtenant_keystring
host.tool_logsReturn the most recent log lines for one of this tenant's tools.
limitintegernamestringrequiredtenant_keystring
host.tool_testDry-run an already-published tool by name, no calls row written; for the other cases see host.quickstart.
argsobjectrequirednamestringrequiredtenant_keystring
host.bridge_testDry-run an unpublished http spec against its real upstream; for the other cases see host.quickstart.
argsobjectrequiredspecobjectrequiredtenant_keystring
host.tool_runDebug-run a published python tool for stdout, stderr and exit code; for the other cases see host.quickstart.
argsobjectrequirednamestringrequiredtenant_keystring
host.tool_callInvoke 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 {run_id, status: "queued"} immediately instead of running inline -- see host.runs.get/wait.
argsobjectrequiredasyncbooleannamestringrequiredtenant_keystring
host.usageCalls, errors and duration percentiles for this tenant over a window.
tenant_keystringwindowstring
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Dual-era
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/dev-mcphost-mcphost)<a href="https://mcpmetrics.io/servers/dev-mcphost-mcphost"><img src="https://mcpmetrics.io/badge/dev.mcphost/mcphost/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- ai.fluxink/fci-mcpmcp.fluxink.ai
Convert handwriting into text, LaTeX math, chemistry, or molecular structures.
- Liepin Jobsopen-agent.liepin.com
Liepin job search and resume workflows backed by the official Liepin MCP server.
- Carrier MCP: Give Your AI Agent Global Connectivitymcp.carrier.llc
Carrier MCP — natural language control of your MVNO/eSIM fleet. 52 tools (43 OCS API wrappers + 8 AI intelligence + 1 OCS event history), 5 prompts, OAuth 2.1 + PKCE. Streamable HTTP on Cloudflare Workers.
- AEO Toolaeotool.io
Audit any website for AI citability on **67 criteria across 7 AI engines** (ChatGPT, Gemini, Perplexity, Claude, Copilot, Grok, Google AI Overviews). Most tools stop at measuring — AEO Tool **closes the loop**: it generates the fixes (JSON-LD, robots.txt, llms.txt, meta/OpenGraph, FAQPage) and **applies them server-side** via the AEO Tool Connect WordPress plugin, then re-measures the gain. Built for **agencies**: audit dozens of client sites in one command (`aeo_batch_audit`), get the prioritized improvement checklist (`aeo_improvements`), apply level-1 fixes (`aeo_apply`), and track AI citations (`aeo_citations`) — all from Claude. **8 tools**: aeo_list_sites, aeo_audit, aeo_batch_audit, aeo_report, aeo_improvements, aeo_generate, aeo_apply, aeo_citations. Auth: OAuth 2.1 (paste your `wl_` API key on the consent screen).
- Publish a webpage to a live URL, straight from your AI.yapp.page
Yapp turns "build me a page and publish it" into a live URL. Connect once (browser OAuth, or a token for terminal clients) and your AI can publish a webpage from HTML, or host a PDF, image, or ZIP exactly as-is to a public `<slug>.yapp.page` URL in seconds, then update, password-protect, set expiry, attach a custom domain, or read form submissions, all by asking. Free to start; no local install. **Tools (15):** `publish_page`, `publish_file`, `update_page`, `delete_page`, `get_page_stats`, `list_my_pages`, `rename_page`, `change_page_slug`, `set_page_expiry`, `set_page_password`, `list_submissions`, `add_custom_domain`, `list_custom_domains`, `check_custom_domain`, `remove_custom_domain`.
Comments
Sign in to write a comment
No comments yet. Be the first.