Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

export_audit_log

Export filtered local audit history to JSONL or CSV for review, including optional time-window, branch, and artifact-type filters; requires Kiln Enterprise.

Instructions

Dump the local reflog to JSONL or CSV.

Needs Kiln Enterprise.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "export_audit_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe most entries to read from the log, newest first, before the time window is applied. Defaults to ``100000``. Default: 100000.
end_timeNoLeave out entries recorded after this moment, in Unix epoch seconds. Omit it for no upper bound.
branch_idNoOnly export entries for this branch id. Omit it for every branch.
start_timeNoLeave out entries recorded before this moment, in Unix epoch seconds. Omit it for no lower bound.
output_pathNoWhere to write the export file. Omitted, Kiln writes it into a new temporary folder of its own and returns that path.
artifact_typeNoOnly export entries for this kind of artifact: ``"design"``, ``"preset"`` or ``"feature"``. Omit it for every kind.
output_formatNo``"jsonl"`` (the default, one JSON object per line) or ``"csv"``. Any other value is refused. Default: "jsonl".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.5.1
    • addedInput schema / properties / artifact_type / description
      Added value: +"Only export entries for this kind of artifact: ``\"design\"``, ``\"preset\"`` or ``\"feature\"``.  Omit it for every kind."
    • addedInput schema / properties / branch_id / description
      Added value: +"Only export entries for this branch id.  Omit it for every branch."
    • addedInput schema / properties / end_time / description
      Added value: +"Leave out entries recorded after this moment, in Unix epoch seconds.  Omit it for no upper bound."
    • changedInput schema / properties / limit / description
      Previous value: -"Default: 100000."New value: +"The most entries to read from the log, newest first, before the time window is applied.  Defaults to ``100000``. Default: 100000."
    • changedInput schema / properties / output_format / description
      Previous value: -"Default: \"jsonl\"."New value: +"``\"jsonl\"`` (the default, one JSON object per line) or ``\"csv\"``.  Any other value is refused. Default: \"jsonl\"."
    • addedInput schema / properties / output_path / description
      Added value: +"Where to write the export file.  Omitted, Kiln writes it into a new temporary folder of its own and returns that path."
    • addedInput schema / properties / start_time / description
      Added value: +"Leave out entries recorded before this moment, in Unix epoch seconds.  Omit it for no lower bound."
  2. Addedv1.5.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, consistent with a tool that reads the log and writes a file. The description adds the Enterprise licensing requirement, which annotations do not convey, but says nothing about whether an existing output_path file is overwritten, how large exports behave, 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?

Two short, front-loaded statements with no filler; the format choice and the access requirement both land immediately. It is perhaps slightly terse for a 7-parameter export tool, but nothing is wasted.

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?

With all parameters optional and no output schema, the description covers the essential call shape and the Enterprise requirement, and the output_path schema text explains the returned path when omitted. Still missing is any note on file overwrite behavior, limits of the default 100000-entry cap, or relationship to the other audit/reflog tools in the catalog.

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 every parameter (limit, start/end time, branch_id, artifact_type, output_path, output_format) is already documented in the schema. The description mentions the JSONL/CSV output formats but merely repeats the output_format parameter without adding new meaning; 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 gives a concrete verb and resource ("Dump the local reflog to JSONL or CSV"), which is more specific than the name alone. However, it labels the resource a "reflog" while the tool is named export_audit_log, and it never distinguishes itself from closely related siblings like export_audit_trail or show_reflog.

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?

"Needs Kiln Enterprise" gives a useful prerequisite gate that tells the agent when the call is even possible. But there is no guidance on when to pick this over export_audit_trail or show_reflog, and no exclusions about export size or scope.

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