DevFlow MCP Server

knowledge_harvest

Retrieve completed flow details, existing ADRs, related drafts, and instructions after a flow is marked done, enabling a decision to create a new knowledge draft or skip when the theme is already covered.

Instructions

Harvest knowledge from a single done-flow. Call this right after flow_update transitions a flow to done (the server's nextStep will remind you). Returns the flow + existing ADRs + related drafts + instructions. Decide: does this flow warrant a new draft? If yes, call knowledge_draft_create. If the theme is already covered, skip.

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": {
      "flowId": "<flowId>"
    },
    "name": "knowledge_harvest"
  }
}

Input Schema

Name	Required	Description	Default
`flowId`	Yes	Flow id to harvest (must be in done state)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv4.35.0Jun 7, 2026

TDQS

A4.2/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It discloses return data: 'Returns the flow + existing ADRs + related drafts + instructions.' However, it does not state whether the tool is read-only or if it has side effects. The lack of annotation or explicit safety info keeps this at a mid score.

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?

The description is concise (two sentences plus a decision directive), front-loaded with purpose, and every sentence adds value. No redundant information.

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?

Given the tool's simplicity (single param, no output schema), the description is largely complete. It explains when to use, what it returns, and next steps. A minor gap is the lack of detail on 'harvest' mechanics, but this is sufficient for the workflow context.

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?

The only parameter 'flowId' has full schema description coverage (100%) with the note 'must be in done state'. The tool description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

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 states the tool's purpose: 'Harvest knowledge from a single done-flow.' It specifies the action (harvest), resource (knowledge from a done-flow), and implicitly distinguishes from siblings like knowledge_draft_create by framing it as a preceding step.

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?

Explicit when to use: 'Call this right after flow_update transitions a flow to done.' Also provides decision guidance: 'Decide: does this flow warrant a new draft? If yes, call knowledge_draft_create. If the theme is already covered, skip.' This clearly indicates when to use alternatives.

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

Deploy Server