Skip to main content
Glama

Save session to library

publish_session
Destructive

Save a session transcript (JSONL), or markdown you composed (format=markdown), to your private a4sx library. The server only rewrites text that matches secret and personal-data patterns (such as tokens, private keys, emails, IP addresses and home-directory user names). It removes no record or field: a raw Claude Code transcript keeps the user's CLAUDE.md and session context (attachment records), file-history snapshot records (absolute file paths), other non-conversation records (such as pr-link), tool-output copies (toolUseResult), and cwd, gitBranch and version on every line; the reply counts them (except version) in unprepared_carriers. Prepare first. Route A, safer when it is enough: compose the decisions, constraints, state and files worth carrying as markdown and send format=markdown. Route B (Claude Code transcripts; other formats: route A), on a copy, never the original transcript: keep only user, assistant and summary records, re-pointing each parentUuid to the nearest kept ancestor (or null); delete cwd, gitBranch, version and toolUseResult; list the hostnames, KEY=value secrets and client or employer names left (show the user counts, not values), and replace the ones the user approves, literally, in decoded strings and object keys. Either way, get the user's explicit yes before sending. Private: it is never listed publicly by this tool.

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": {
      "transcript": "<transcript>"
    },
    "name": "publish_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNo
titleNo
formatNojsonl: a transcript. markdown: content you composed (route A: the decisions, constraints, state and files worth carrying); stored as sent, after the same server scrub.jsonl
parentNoLibrary id this session continues from (lineage).
transcriptYesThe session transcript as JSONL (Claude Code or Codex CLI format; detected automatically), or markdown you composed with format=markdown.
visibilityNoAlways private. Listing publicly is a separate step in the web app.private
content_sha256NoHex SHA-256 of the transcript's UTF-8 bytes; checked.
client_scrubbedNoThe client scrubbed before sending. The server scrubs again regardless.
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / format / description
      Previous value: -"jsonl: a transcript. markdown: content you composed (route A in GET /orient on this server without auth); stored as sent, after the same server scrub."New value: +"jsonl: a transcript. markdown: content you composed (route A: the decisions, constraints, state and files worth carrying); stored as sent, after the same server scrub."
  2. Changed2 schema fields changed
    • addedInput schema / properties / format
      Added value: +{
      +  "default": "jsonl",
      +  "description": "jsonl: a transcript. markdown: content you composed (route A in GET /orient on this server without auth); stored as sent, after the same server scrub.",
      +  "enum": [
      +    "jsonl",
      +    "markdown"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / transcript / description
      Previous value: -"The session transcript as JSONL (Claude Code or Codex CLI format; detected automatically)."New value: +"The session transcript as JSONL (Claude Code or Codex CLI format; detected automatically), or markdown you composed with format=markdown."
  3. Changed1 schema field changed
    • changedInput schema / properties / transcript / description
      Previous value: -"The session transcript as JSONL (Claude Code format)."New value: +"The session transcript as JSONL (Claude Code or Codex CLI format; detected automatically)."
  4. First observed

TDQS

A4/5.0
Behavior5/5

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

Beyond destructiveHint=true, it explains exactly what the server does and does not scrub, lists retained sensitive carriers (CLAUDE.md, absolute file paths, toolUseResult, cwd, gitBranch, version), mentions unprepared_carriers in the reply, and stresses private storage. This is unusually rich disclosure for a destructive write.

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 purpose is front-loaded, but the remainder is a dense run-on paragraph mixing server behavior, Route A, Route B, consent, and privacy. The content is largely relevant, yet bullet points or shorter sentences would make it much easier to act on.

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 9-parameter destructive save with no output schema, it covers the privacy model, scrubbing limitations, preparation alternatives, and consent requirements well. It still omits the success response (e.g., whether a library id is returned) and the meaning of label, title, and idempotency_key, leaving some operational gaps.

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 67%, with descriptions for format, transcript, visibility, content_sha256, client_scrubbed, and parent. The prose adds useful meaning about format=markdown and transcript handling, but it never explains label, title, or idempotency_key, so it only partially compensates.

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 opening sentence names the verb (Save), the two resource forms (JSONL transcript or composed markdown), and the destination (private a4sx library). It does not explicitly distinguish this write operation from read-oriented siblings such as fetch_session_context or search_sessions, so it falls short of 5.

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 gives explicit preparation guidance: prepare first, choose Route A (markdown) when sufficient or Route B for Claude Code transcripts on a copy, and obtain the user's explicit yes before sending. It does not compare against sibling tools or state when not to use this tool, so not a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.