agentswitchboard

Connect Bundle

connect_bundle

Read-onlyIdempotent

One MCP client config to paste ({"mcpServers": …}, as Cursor and other MCP clients read it) for up to 10 listings, and how each one connects. A listing is in the config when its own docs give a hosted server address or a local command. An MCP server whose docs give neither comes with its setup guide, and setupPrompt asks a coding agent to set all of those up. A listing without an MCP server comes with its CLI install command, API address or docs. Also returns a claude mcp add command for each server in the config, for Claude Code, and the /stack link for the listings. Nothing is guessed: every address and command is copied from the vendor's docs, as on the listing's page.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "slugs": "<slugs>"
    },
    "name": "connect_bundle"
  }
}

Input Schema

Name	Required	Description	Default
`slugs`	Yes	Listing slugs, in the order to list them: 1 to 10, e.g. a stack's items

Output Schema

Name	Required	Description
`items`	Yes
`notes`	Yes	Named listings that were left out, and why
`config`	Yes	The MCP client config to paste; null when no listing has an address or command to copy
`summary`	Yes	How many are in the config, to set up from a guide, and without an MCP server
`stackUrl`	Yes	These listings as a shared stack on the site
`claudeCode`	Yes	A claude mcp add command for each server in the config
`setupPrompt`	Yes	For a coding agent: set up each MCP server that has only a setup guide

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 2, 2026

removedOutput schema / properties / items / items / properties / featured

Removed value: -{
-  "description": "Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.",
-  "type": "boolean"
-}

changedOutput schema / properties / items / items / required

Previous value: -[
-  "name",
-  "slug",
-  "url",
-  "iconUrl",
-  "description",
-  "provider",
-  "categories",
-  "accessMethods",
-  "verified",
-  "official",
-  "featured",
-  "authType",
-  "how",
-  "server",
-  "docsUrl",
-  "note"
-]New value: +[
+  "name",
+  "slug",
+  "url",
+  "iconUrl",
+  "description",
+  "provider",
+  "categories",
+  "accessMethods",
+  "verified",
+  "official",
+  "authType",
+  "how",
+  "server",
+  "docsUrl",
+  "note"
+]

AddedNov 2, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavioral context: the inclusion rule (a listing is in the config only if its docs give a hosted address or local command), the fallback for servers lacking either (setup guide + setupPrompt for a coding agent), the fallback for listings with no MCP server (CLI install command, API address, docs), and the guarantee that nothing is guessed. It does not describe pagination or failure behavior for bad slugs, but the fallback logic disclosed is substantive.

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

Conciseness3/5

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

The core payload is front-loaded in the first clause, which is good, but the remainder is a run-on of comma-joined fragments that mix inclusion rules, fallbacks, and secondary outputs. The 'claude mcp add … for Claude Code' and /stack sentences could be compressed, and the closing 'as on the listing's page' is a redundant flourish.

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?

With an output schema present, the description need not enumerate return values, yet it still explains the two config paths, the setupPrompt fallback, and the auxiliary outputs — enough for an agent to call this correctly and interpret the result. The only material hole is the unresolved 10-vs-30 limit and the absence of any error behavior for unknown slugs.

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

Parameters3/5

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

Schema coverage is 100% and there is only one parameter, so the schema already documents the slugs array and its ordering. However, the description states 'up to 10 listings' while the schema declares maxItems 30, a direct conflict that leaves the agent unsure of the true cap — that inconsistency is a real semantic gap rather than a mere omission.

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

Purpose4/5

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

The description makes clear that this returns a paste-ready MCP client config ({"mcpServers": …}) for a set of listings, plus per-server 'claude mcp add' commands and a /stack link, which is enough to distinguish it from get_agent or search_agents. The weakness is that the verb is implicit — it describes the artifact rather than saying 'generates/builds a config', so an agent must infer the action from the noun phrase.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer you call this when you want a connect config for a group of listings (the schema hints 'e.g. a stack's items'). There is no explicit when-to-use vs. when-not, and no sibling is named as an alternative — e.g. it never says to use get_agent for a single listing or search_agents to find slugs first.

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

All agentswitchboard tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.