Kaiku

Create or update MCP connection

upsert_mcp_connection

Destructive

Admin only: create or update a project's external MCP connection. Pass 'id' to update an existing one (omit to create). 'token' is stored server-side and never returned; omit it to keep the current token when updating. The assistant panel calls the server's read-only tools (readOnlyHint) directly and turns every other non-destructive tool into a card the person applies; 'forAgents' also gives the project's agents its read-only tools.

Input Schema

Name	Required	Description
`id`	No	Existing connection id to update; omit to create a new one.
`url`	No	MCP server URL — use https (required when creating).
`name`	No	Connection display name (required when creating).
`token`	No	Bearer auth token. Omit to keep the current token when updating.
`enabled`	No	Whether the connection is enabled.
`forAgents`	No	Whether the project's agents (called by a mention, a reply or a duty) also get this server's read-only tools. Off by default.
`projectKey`	Yes	Project key, e.g. 'UK'.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

addedInput schema / properties / forAgents

Added value: +{
+  "default": null,
+  "description": "Whether the project's agents (called by a mention, a reply or a duty) also get this server's read-only tools. Off by default.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

First observedSep 22, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so mutation safety is covered structurally. The description adds genuinely non-obvious behavior: the token is stored server-side and never returned, omitting it preserves the current token, and a connection's tools feed the assistant panel and optionally project agents. It omits what an update can destroy or overwrite, which keeps it short of a 5.

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?

Four tight sentences with the critical admin scope and id rule front-loaded. The closing sentence on assistant-panel behavior is longer than strictly needed but ties directly to the forAgents parameter rather than wandering.

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?

For a 7-param mutation with no output schema but full schema descriptions and annotations, the description covers create/update branching, secret handling, and the controlled side effects on agents. Nothing an agent needs before calling 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 baseline is 3. The description nonetheless adds semantics beyond the schema: token secrecy and preservation-on-omit, and a substantive explanation of what forAgents actually grants, which the schema text only gestures at.

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 pair (create/update) and resource (project's external MCP connection), plus an admin-only scope qualifier. The upsert nature is disambiguated by the id rule, so an agent knows exactly what the tool targets.

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?

Gives explicit create-vs-update selection logic ('Pass id to update; omit to create') and token-omission behavior. It doesn't name alternatives such as list_mcp_connections for discovery, but the core invocation conditions are stated plainly.

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

All Kaiku tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?