shiply

Mount a site at a path

set_link

Idempotent

Path-mounting: serve an owned target site at a path on an owned host site (host/docs -> target). location is a path like "docs", or "root" for the host root. Both sites must be owned by you. Pass remove=true to unmount.

Input Schema

TableJSON Schema

Name	Required	Description
`remove`	No	unmount instead of mounting
`hostSlug`	Yes	slug of the owned host site
`location`	Yes	path to mount at, e.g. "docs", or "__root__" for the host root
`targetSlug`	No	slug of the owned site to serve there (required unless remove=true)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

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

Changed5 schema fields changedJun 23, 2026

addedInput schema / properties / hostSlug / description
```
Added value: +"slug of the owned host site"
```

addedInput schema / properties / location / description

Added value: +"path to mount at, e.g. \"docs\", or \"__root__\" for the host root"

addedInput schema / properties / remove / description
```
Added value: +"unmount instead of mounting"
```

addedInput schema / properties / targetSlug / description

Added value: +"slug of the owned site to serve there (required unless remove=true)"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "result": {}
+  },
+  "required": [
+    "result"
+  ],
+  "type": "object"
+}

First observedJun 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations declare idempotentHint=true, and the description adds behavior: ownership requirement, path format ('docs' or '__root__'), and the ability to unmount. No contradiction.

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?

Three sentences, front-loaded with the core concept. Every sentence adds necessary information without redundancy.

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?

The description covers the primary use cases (mount/unmount) and prerequisites. An output schema exists, so return values need not be explained. It is complete for a tool of this complexity.

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

Parameters4/5

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

Schema has 100% coverage with descriptions, but the description adds value by explaining the purpose of location (path examples) and the conditional requirement for targetSlug. This enhances understanding beyond the schema.

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 clearly defines the tool's purpose: path-mounting a target site on a host site. It uses specific verbs ('serve', 'mount') and explains the resource relationship (host/docs -> target). It also distinguishes from siblings by its unique function.

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?

The description states the context for use ('Both sites must be owned by you') and explains the remove flag for unmounting. It does not explicitly list alternatives, but the context is clear enough for most use cases.

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

All shiply tools Inspect

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

B3.4/5.0

Disambiguation2/5

Many tools have overlapping purposes (e.g., add_domain, add_subdomain, add_custom_domain, add_sending_domain) or similar names like check_domain and check_custom_domain, which can confuse an agent. While descriptions help, the sheer number of closely related tools makes it difficult to consistently select the correct one.

Naming Consistency3/5

Most tools follow a verb_noun pattern, but there are exceptions like 'read_thread' (instead of get_thread) and 'mark_thread_read' (verb_noun_verb). Prefixes like 'data_' are used inconsistently with other tools, but overall the naming is still readable.

Tool Count1/5

With 103 tools, the server is extremely bloated. Even for a comprehensive platform, this count overwhelms any agent and makes the tool surface difficult to navigate. Many tools could be merged or are too granular.

Completeness4/5

The toolset covers a wide range of operations across sites, domains, email, marketplace, projects, contracts, and functions. While some updates (e.g., general contract editing) are missing, the surface is mostly comprehensive for the domain.

Resources

Need Help?