Skip to main content
Glama
Sign In
Syncthing MCP

Syncthing MCP

by si-essence
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

syncthing_system

Destructive

Check Syncthing system health, status, connections, discovery, and errors, then preview or confirm pause, resume, restart, and shutdown actions.

Instructions

System health, ping, status, version, connections, discovery, errors, pause, resume, restart, and shutdown. Writes run only when confirm is true and SYNCTHING_ALLOW_WRITES=true. Omit confirm or pass false for a preview that sends nothing. Actions: health, ping, status, version, connections, discovery, errors, error_clear, pause, resume, restart, shutdown.

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": {
      "action": "<action>"
    },
    "name": "syncthing_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesSyncthing operation to call.
deviceNoDevice id query for pause, resume, pending folders, and completion.
confirmNoBoolean true runs the write when SYNCTHING_ALLOW_WRITES is true. Omit it or pass false for a dry-run preview that sends nothing. The string true is rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, and the description adds meaningful context beyond them: the two-key write gate, the fact that omitting confirm produces a dry-run that sends nothing, and that a string 'true' is rejected. It still does not say which actions are the destructive ones (restart, shutdown, error_clear) or what state they lose, but the safety-relevant behavior is well disclosed.

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

Conciseness3/5

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

The write-gating sentence is front-loaded and high value, but the action list is enumerated twice — once in the first sentence and again in full at the end, differing only by the addition of error_clear. That duplication costs space without adding information.

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?

For a twelve-action multiplexer wrapping destructive daemon controls, the description covers the write gate but leaves each action's effect and return shape unexplained, and the device parameter's role is unstated. With no output schema, an agent still has to infer what individual actions do and what data comes back.

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 100%, so the enum, confirm, and device semantics are already documented in the schema; the description largely restates the same enum and the confirm gate. The device parameter is never mentioned in the prose, so no meaning is added beyond the structured fields. Baseline 3 applies.

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 description opens with a concrete resource (system) plus an enumerated action set (health, ping, status, version, connections, discovery, errors, pause, resume, restart, shutdown), which is enough for an agent to tell this is the catch-all system/daemon-control tool rather than config, db, devices, or folders. It is clear but the purpose is conveyed by enumeration rather than a stated scope sentence, so there is no explicit differentiation from the siblings.

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 strong invocation guidance for writes (confirm=true plus SYNCTHING_ALLOW_WRITES=true, otherwise a preview) but says nothing about when to pick this tool over syncthing_config, syncthing_devices, or the others. Usage is implied by the action names, not by stated selection criteria.

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