Skip to main content
Glama

mcphost

by dev.mcphost

host.tool_publish

Publish a tool of a registered kind under this tenant's namespace. Minimal example spec per kind: echo -- spec: {"schema":{"properties":{"msg":{"type":"string"}},"required":["msg"],"type":"object"}}. spec.schema is any JSON Schema; a call echoes back the arguments it was given, validated against it. http -- spec: {"method":"GET","url":"https://api.example.com/items/{{id}}"}. url must be an absolute https URL; method and url are the only required fields -- args_schema is inferred from the url/header/body templates when omitted. python -- spec: {"source":"def main(args):\n return {"doubled": args["n"] * 2}\n"}. only source is required -- args_schema and requirements are both inferred from it (tool-infer, v0.4.0); source must define main(args). Name must match ^[a-z][a-z0-9_]{1,40}$. A rejection names the failing field, what was expected, and a corrected example -- fix it and resubmit. Try host.tool_test on a published tool before a real call, or call host.quickstart(kind) for a filled-in worked example.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYes
nameYes
specYes
tenant_keyNoThe key `signup` returned. Required only when this connection carries no Authorization: Bearer header -- when both are present, the header wins.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral disclosure burden and meets it. It reveals name validation rules, rejection message contents, spec inference behavior, and per-kind requirements. This lets an agent anticipate both validation failures and how spec processing works.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but dense and well-structured: purpose first, then concrete spec examples, then validation and follow-up guidance. Every block earns its place, and the embedded examples are essential for correct invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It covers required parameters, spec variants, validation rules, failure behavior, and suggested next steps. The only notable gaps are the lack of explicit information about the success response shape and whether republishing an existing name overwrites or rejects. These are minor given the overall richness of the definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25%, and the description compensates thoroughly. It explains what name must look like, what kind means via concrete examples, and exactly what spec shapes are valid for echo/http/python. This adds significant meaning beyond the raw schema fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear action and scope: 'Publish a tool of a registered kind under this tenant's namespace.' It also enumerates concrete kind examples (echo, http, python), so an agent can tell exactly what the tool does and can distinguish it from siblings like host.registry_publish.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives practical follow-up guidance, such as trying host.tool_test before a real call or calling host.quickstart(kind) for a worked example. It does not explicitly contrast with host.registry_publish or state when not to use the tool, but the phrase 'registered kind' and the per-kind spec examples provide strong contextual guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mcphost toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools target a clearly distinct resource or lifecycle stage, with billing, secret, and tool-publishing groups nicely separated. The main ambiguity is among host.tool_call, host.tool_test, and host.tool_run, which all invoke a published tool in slightly different modes; the descriptions clarify this, but the names alone could mislead an agent.

Naming Consistency4/5

The namespace prefixes billing.* and host.* provide a consistent organizational pattern, and host.tool_* tools use a predictable resource-action style. Deviations like signup, host.quickstart, host.usage, and host.whoami break the pattern, but they are few and still readable.

Tool Count4/5

At 17 tools, the server is slightly over the typical well-scoped 3-15 range, but the breadth is justified by the multi-tenant hosting domain: signup, billing, tool lifecycle, secrets, debugging, and usage observability each need dedicated tools. Every tool has a plausible role, so the count feels reasonable rather than bloated.

Completeness3/5

The tool lifecycle is well covered with publish, list, test, run, call, logs, and remove, and billing/usage/signup are present. Notable gaps remain, though: secret_set has no corresponding secret_delete, there is no tenant update/delete operation, and host.registry_publish references admin.tenant_verify_namespace, which is not exposed in this tool set.

Resources