Skip to main content
Glama
Sign In
KrakenMCP

KrakenMCP

by gateniomer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

chain

Runs a sequence of planning, execution, and review stages with fix rounds, pausing when autonomy requires developer input and returning an ID to check status, resume, or cancel.

Instructions

Run a chain of tentacle stages (default: plan -> execute -> review, with fix rounds). Each stage's autonomy decides whether it continues or waits for the developer. Returns a chain_id for status, resume and cancel.

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": {
      "task": "<task>"
    },
    "name": "chain"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoRepository path
nameNoChain name (default "default")
taskYesInclude the developer's answers to open questions
verifyNoCommand to run after each write step, e.g. "npm test"
sessionNoRun group labeldefault
overridesNo
context_runsNoFinished run ids to pass in as context
max_fix_roundsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.3

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses genuinely important behavior: stages may pause and wait for the developer based on autonomy, and fix rounds occur. However, it says nothing about the fact that this drives coding agents that modify the repository, whether the call blocks until completion, or what happens on failure mid-chain.

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?

Three compact sentences, front-loaded with the default pipeline before behavioral and return-value details. No wasted wording, though "Each stage's autonomy decides" leans on a jargon term the reader must infer.

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?

For an 8-parameter orchestration tool with no annotations and no output schema, the description covers the pipeline shape, the pause/resume behavior, and the return value (chain_id) with its follow-up tools. Gaps remain around overrides, verification semantics, and failure handling, but the essentials for a correct first call are present.

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 75%, so the schema already documents most parameters including task, verify, context_runs and cwd. The description only indirectly touches max_fix_rounds through the phrase "fix rounds" and adds nothing about overrides (per-stage agent/model/effort) or session grouping, so it does not compensate for the remaining gap.

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?

"Run a chain of tentacle stages" gives a specific verb and resource, and the parenthetical default pipeline (plan -> execute -> review) makes the scope concrete. It is distinguishable from single-stage siblings like run/plan/execute/review, though it never names them explicitly as alternatives.

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?

The description establishes clear context for use (orchestrating multiple stages with fix rounds) and usefully routes follow-up actions by stating the returned chain_id feeds status, resume and cancel. It stops short of explicit exclusion guidance such as "use run for a single stage instead".

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

Deploy Server

Other Tools