flowforge-mcp

flowforge_manage_mcp_servers

Destructive

Manage MCP servers that FlowForge assistants can call mid-conversation by attaching registry or custom servers, inspecting tools, testing custom endpoints, and enabling org-wide server access.

Instructions

Manage the MCP servers FlowForge assistants can call mid-conversation.

Attach a server to an assistant by adding its ID to the assistant's mcp_servers (flowforge_update_assistant). Use custom_test and custom_call to verify a custom server before attaching it.

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": {
      "params": "<params>"
    },
    "name": "flowforge_manage_mcp_servers"
  }
}

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 6, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds that custom servers should be verified before attaching, which is real operational context, but it never flags that org_set REPLACES the entire enabled list or that confirm=true is mandatory for the destructive actions — the riskiest behaviors here.

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?

Two short sentences, front-loaded with the purpose, no filler or repetition. It is arguably too terse for a ten-action destructive tool, but as written every sentence earns its place.

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

Completeness3/5

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

An output schema exists, so return values need not be described. However, this is a destructive, non-idempotent, open-world tool with ten actions, and the description covers only the custom-server verification path while omitting catalog, server_tools, and the org_list/org_set/org_remove family entirely.

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?

Reported schema coverage is 0%, so the description must compensate, and it only partially does: it names mcp_servers as the attach point and highlights custom_test/custom_call. It never explains the action enum, the confirm flag, or which fields belong to which action; that burden falls entirely on the nested property descriptions, which the top-level schema summary does not reflect.

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 first sentence names a specific resource (MCP servers callable by FlowForge assistants mid-conversation) and a management verb, scoping it away from call/campaign/assistant tools. It does not, however, distinguish the ten distinct sub-operations, so an agent cannot tell from the description alone whether this tool also does org-level enablement or catalog browsing.

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?

It gives one useful routing instruction: attaching a server is done via flowforge_update_assistant by adding the ID to mcp_servers, and custom_test/custom_call should be used to verify before attaching. That is a genuine workflow hint, but there is no when-to-use guidance across the ten actions (catalog vs. org vs. custom) and no when-not to use it.

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

Deploy Server