Is the Mcphost Host MCP server down?

mcp-registry/dev.mcphost/mcphost · v0.118.2+contract.1.153248809200

healthy
Last checked 2026-10-26 18:01 UTC · handshake 592ms

As of 2026-10-26 18:01 UTC, the Mcphost Host MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.

uptime (30d checks)
100%
checks observed
5,060
outages (90d)
0
tools
18

Host your MCP tool over streamable HTTP in one command.

Point your MCP client at this streamable-http endpoint: https://mcphost.dev/mcp

Agent-readiness: C (73/100)

C (73/100): 0 error(s), 5 warning(s) across 18 tool(s); ~9,595 tokens of tool definitions.
Scores higher than 8% of 15,768 MCP servers Glimind has audited.
Its tool list costs an agent ~9,595 tokens per session — more than 80% of servers.
69 → 73 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions100
Safety hints7
Token cost87
Client compatibility50
Protocol100
Reliability100
Stability20

What to fix (5)

1 tool definition(s) exceed ~1,200 tokens each (largest: host.tool_publish, ~3,189).

Move long reference material out of descriptions (link a doc or expose a resource), drop repeated examples, and collapse large enums. Trimming these to ~600 tokens saves ~2,589 tokens every session. How to fix →

Tools: host.tool_publish · saves ~2,589 tokens/session

18 of 18 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: billing.plans, host.errors, host.feedback.list, host.feedback.send, host.help.get and 13 more

17 tool name(s) contain "." or exceed 64 characters, which OpenAI-compatible function calling rejects (^[a-zA-Z0-9_-]{1,64}$).

Use "_" or "-" instead of "." and keep names to 64 characters, so clients built on OpenAI-style tool calling don't have to rename (or drop) them. How to fix →

Tools: billing.plans, host.errors, host.feedback.list, host.feedback.send, host.help.get and 12 more

3 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: host.feedback.send, host.state.set, host.tool_publish

In the last 30 days: 135 tool(s) removed and 349 schema change(s).

Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →

Auto-fix: 17 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fdev.mcphost%2Fmcphost/fixes

billing.plans 1 change
{
  "name": "billing_plans",
  "description": "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.",
  "inputSchema": {
    "type": "object",
    "required": [],
    "properties": {
      "tenant_key": {
        "type": "string",
        "description": "The key `signup` returned. Optional on the connection that ran signup (or host.redeem): that connection is already bound to the tenant it created, so later calls on it need no tenant_key. On a connection with no Authorization: Bearer header and no prior signup, omitting it implicitly signs that connection up as a brand-new tenant and runs this call as it -- see host.whoami's source field. When both a header and this argument are present, the header wins."
      }
    },
    "x-mcphost-validated": true,
    "additionalProperties": false
  }
}
host.errors 1 change
{
  "name": "host_errors",
  "description": "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.",
  "inputSchema": {
    "type": "object",
    "required": [],
    "properties": {
      "code": {
        "type": "string",
        "description": "An error code, e.g. tool_exception. Omit to list every code."
      },
      "tenant_key": {
        "type": "string",
        "description": "The key `signup` returned. Optional on the connection that ran signup (or host.redeem): that connection is already bound to the tenant it created, so later calls on it need no tenant_key. On a connection with no Authorization: Bearer header and no prior signup, omitting it implicitly signs that connection up as a brand-new tenant and runs this call as it -- see host.whoami's source field. When both a header and this argument are present, the header wins."
      }
    },
    "x-mcphost-validated": true,
    "additionalProperties": false
  }
}
host.feedback.list 2 changes
{
  "name": "host_feedback_list",
  "description": "List your own feedback (newest first, status received). Anonymous callers get [].",
  "inputSchema": {
    "type": "object",
    "required": [],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Max rows, up to 100; default 20."
      },
      "tenant_key": {
        "type": "string",
        "description": "The key `signup` returned. Optional on the connection that ran signup (or host.redeem): that connection is already bound to the tenant it created, so later calls on it need no tenant_key. On a connection with no Authorization: Bearer header and no prior signup, omitting it implicitly signs that connection up as a brand-new tenant and runs this call as it -- see host.whoami's source field. When both a header and this argument are present, the header wins."
      }
    },
    "x-mcphost-validated": true,
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/dev.mcphost/mcphost"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/dev.mcphost/mcphost"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.mcphost%2Fmcphost.svg)](https://glimind.com/server/mcp-registry%2Fdev.mcphost%2Fmcphost?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fdev.mcphost%2Fmcphost?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.mcphost%2Fmcphost.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.mcphost%2Fmcphost.svg
   :target: https://glimind.com/server/mcp-registry%2Fdev.mcphost%2Fmcphost?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:ee0a2389f36771ac…, first seen 2026-10-24, included at leaf 59535 of 74,588. Version history · verify what your client received.

Tools (18)

Compare: most reliable other servers · most reliable communication servers · most reliable knowledge servers · most reliable security servers · most reliable database servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Mcphost Host MCP server down right now?

As of 2026-10-26 18:01 UTC, the Mcphost Host MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.

How many tools does Mcphost Host MCP server provide?

Mcphost Host MCP server advertises 18 tools, including billing.plans, host.errors, host.feedback.list, host.feedback.send, host.help.get.

How do I install Mcphost Host MCP server?

Point your MCP client at this streamable-http endpoint: https://mcphost.dev/mcp

Is the Mcphost Host MCP server safe to connect to an AI agent?

Glimind scanned all 18 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Mcphost Host MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve