Skip to main content
Glama
Sign In
twincat-mcp

twincat-mcp

by Disectron
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

rec_export

Read-only

Export a PLC signal recording to CSV in wide or long format for analysis, with optional forward-fill for charting.

Instructions

Export a recording to CSV. csv_wide: one row per PLC sample time, one column per variable and per array element (name[i]); an empty cell means no sample of that variable at that time (fill=true forward-fills — handy for charts, but a cell then no longer means "sampled now"). csv_long: t_ms,symbol,value. Both include plc_filetime (the PLC's own sample timestamp) when available. Default path next to the JSONL. An out_path must be in a folder this server writes to ([server] output_dirs adds more). An existing file — also an earlier export at the default path with other symbols/fill, or of a recording that has grown since — is only replaced with overwrite=true; an identical re-export (same source bytes and parameters) is not refused.

Input Schema

NameRequiredDescriptionDefault
idYes
fmtNocsv_wide
fillNo
symbolsNo
out_pathNo
overwriteNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.12
    • addedInput schema / properties / fill
      Added value: +{
+  "default": false,
+  "title": "Fill",
+  "type": "boolean"
+}
    • addedInput schema / properties / overwrite
      Added value: +{
+  "default": false,
+  "title": "Overwrite",
+  "type": "boolean"
+}
  2. First observedv0.6.0

TDQS

A4.5/5.0
Behavior5/5

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

With annotations already declaring readOnlyHint and destructiveHint=false, the description still adds substantial behavioral context: default output location, the output_dirs restriction on out_path, that existing files (including earlier exports or grown recordings) are only replaced with overwrite=true, and that an identical re-export is idempotently not refused. The empty-cell/fill semantics and plc_filetime caveat are also behavior, not schema.

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?

The purpose leads and every subsequent clause carries information, but it is a dense run-on paragraph mixing format semantics, path rules, and overwrite rules with a chatty aside ('handy for charts, but...'). Slightly tighter structure would improve scanability.

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 a 6-parameter tool with 0% schema coverage and an output schema (so return values need not be described), the description covers formats, fill behavior, timestamps, path safety, and overwrite/idempotency. The remaining gap is the symbols and id parameters, whose semantics an agent must still infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the burden, and it explains fmt (csv_wide vs csv_long layouts), fill, out_path constraints, and overwrite semantics well beyond the bare schema. It is weaker on 'symbols' (only implied by 'other symbols/fill') and 'id', which are never characterized as a recording identifier.

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 first sentence states a specific verb and resource ('Export a recording to CSV'), which distinguishes it from sibling exporters such as scope_export or ads_export and from rec_read/rec_snapshot. An agent can identify the operation without opening the schema.

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?

It explains the choice between the two formats, when fill=true is helpful (charts) and its pitfall, and the conditions under which out_path/overwrite are needed. It does not, however, name the alternative tools (rec_read, rec_snapshot) for agents who want data without a CSV file.

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