Skip to main content
Glama
Sign In
Syncthing MCP

Syncthing MCP

by si-essence
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

syncthing_db

Destructive

Inspect Syncthing folder and device database status, pending needs, file metadata, errors, completion, and statistics; trigger a gated folder scan only with confirmation.

Instructions

Folder status, need, file metadata, errors, completion, scan, and folder/device statistics. scan is a write. Writes run only when confirm is true and SYNCTHING_ALLOW_WRITES=true. Actions: status, need, file, errors, completion, scan, folder_stats, device_stats.

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_db"
  }
}

Input Schema

NameRequiredDescriptionDefault
subNoOptional sub path for scan. Empty string is sent when set.
fileNoRelative file path for db file metadata.
pageNo
delayNoScan delay in seconds. Zero is sent when set.
actionYesSyncthing operation to call.
deviceNoDevice id query for pause, resume, pending folders, and completion.
folderNoFolder id query for db status, need, file, errors, completion, and scan.
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.
perpageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real context beyond them: only scan is a write, writes are gated on both confirm=true and the SYNCTHING_ALLOW_WRITES environment flag, omitting confirm yields a dry-run preview that sends nothing, and the string 'true' is rejected. That is unusually specific safety information. It stops short of saying what a scan actually changes on disk or what happens on partial failure.

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 short sentences, front-loaded with the capability list and the write warning before the action enumeration. The action names are stated twice (once in prose, once in the 'Actions:' list), which is mild redundancy, but nothing is padded or buried.

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?

This is a nine-parameter, eight-action tool with no output schema, so the description carries a lot of weight and does not say what any action returns or how paging works for list-style actions like need and errors. The write-gating is complete, but the per-action contract is left to the schema and to experimentation.

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 78%, so the schema already documents most parameters including confirm's dry-run semantics, which the description partly repeats. The description does not explain which parameters pair with which action, nor does it touch page/perpage, so it adds little beyond the structured fields. Baseline 3 applies given the high coverage.

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 names the resource domain (Syncthing database) and enumerates the concrete operations: status, need, file metadata, errors, completion, scan, folder_stats, device_stats. That is enough to separate it from syncthing_config, syncthing_devices, syncthing_folders and syncthing_system, but it never explicitly states the distinction, leaving the agent to infer it from the sibling names.

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?

The write path is well covered: 'scan is a write' and 'Writes run only when confirm is true and SYNCTHING_ALLOW_WRITES=true' tells the agent exactly the precondition for the one mutating action. However there is no guidance on when to pick this tool over the sibling tools, nor on which action to choose for a given question (e.g. need vs completion vs folder_stats).

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