Convocore

create_mcp_connect_link

Connect another MCP server (e.g. https://mcp.notion.com/mcp, https://mcp.linear.app/mcp, https://mcp.atlassian.com/v1/sse) so agents can use its tools. Signing in to that server needs the USER in their own browser, so you cannot do it for them: create the link, show the returned url as a clickable link, and ask them to say when they are done. The page needs no dashboard login, opens on the agency's own domain for whitelabel workspaces, and has one Connect button. Pass agentIds to put the server on those agents automatically once the sign-in finishes (start node; allNodes=true for every node). Pass connectionId to re-sign an existing connection whose sign-in expired. When the user says they finished, call get_mcp_connection and only say it works when status is "connected".

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": {
      "serverUrl": "<serverUrl>"
    },
    "name": "create_mcp_connect_link"
  }
}

Input Schema

Name	Required	Description
`agentIds`	No	Agents to attach the connection to after sign-in.
`allNodes`	No	Attach to every node of those agents instead of only the start node.
`serverUrl`	Yes	The MCP server URL (streamable HTTP or SSE).
`serverName`	No	Short name used in tool names (letters, digits, _ and -). Defaults from the URL.
`ttlMinutes`	No	How long the link works. Default 60, max 10080 (7 days).
`connectionId`	No	Re-sign this existing connection instead of creating a new one.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the mutation/safety profile; the description adds material context beyond them: the user must authenticate in their own browser, the page requires no dashboard login, renders on the agency's domain for whitelabel workspaces, and exposes a single Connect button. This is exactly the auth/UX behavior an agent needs and cannot infer from the schema.

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

Conciseness4/5

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

Front-loaded with the purpose, then the user-interaction constraint, then parameter behavior and the verification step. The whitelabel-domain sentence is slightly tangential, but nearly every clause carries operational value.

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

Completeness5/5

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

With six parameters, no output schema, and mutation semantics, the description still covers the return value (a URL to display), the hand-off to the user, and the verification path via get_mcp_connection. Nothing needed to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics: agentIds attaches the server after sign-in (start node by default; allNodes=true for every node) and connectionId is specifically for re-signing a connection whose sign-in expired. Only ttlMinutes and serverName are left to the schema alone.

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?

States a specific verb and resource (create a connect link for another MCP server) plus the outcome (agents can use its tools), with concrete URL examples. It is clearly separable from siblings like create_channel_connect_link, attach_mcp_connection, and get_mcp_connection, the last of which it names.

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

Usage Guidelines5/5

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

Explicitly says when to use it (connecting an external MCP server), what the agent cannot do (complete sign-in on the user's behalf), and the required follow-up flow: show the URL, wait for the user, then call get_mcp_connection and only confirm when status is "connected". It also states the conditions selecting agentIds and connectionId.

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

All Convocore 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.

Resources

Need Help?