Skip to main content
Glama
Sign In
session-checkpoint-mcp

session-checkpoint-mcp

by daniel-munoz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

List session checkpoints

list_session_checkpoints
Read-onlyIdempotent

Lists saved session checkpoints newest first, showing each goal, last-saved time, branch, and task status so users can choose an older session to resume.

Instructions

List the checkpoints saved in the project (one per Claude Code session, plus a legacy .claude-checkpoint if present), newest first, with each one's goal, last-saved time, branch and whether all its tasks are done. Use it when the user wants to resume a different or older session; load one with load_session_checkpoint's checkpoint.

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": "list_session_checkpoints"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of checkpoints to return, newest first. 0 returns all of them.
projectRootNoAbsolute path of the project. Defaults to the client's workspace root or the server's working directory.

Output Schema

NameRequiredDescriptionDefault
pathYes
textYes
totalYes
entriesYes
omittedYes
warningsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A4.5/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description earns credit for going beyond that with ordering (newest first), cardinality (one per session, plus the legacy file), and a preview of what each row contains, which tells an agent what it can decide without a follow-up call. It stops short of noting pagination/truncation behavior beyond what the schema's limit already implies.

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

Conciseness5/5

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

Two sentences, no filler. The identification and contents come first, followed by the routing guidance, which is the correct front-loading for an agent scanning for tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape needn't be explained, yet the description still summarizes the useful per-entry fields. With annotations covering safety and 100% schema coverage on the two optional params, nothing an agent needs to select or invoke this correctly is missing.

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%, with both `limit` (including '0 returns all') and `projectRoot` documented in the schema, so the baseline is 3. The description repeats 'newest first' but adds no new meaning about default project resolution or the interaction between limit and the legacy entry.

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 description opens with a specific verb and resource ('List the checkpoints saved in the project') and immediately scopes it: one per Claude Code session plus an optional legacy '.claude-checkpoint', ordered newest first, with the fields each entry carries (goal, last-saved time, branch, task completion). That level of detail distinguishes it cleanly from save_session_checkpoint and load_session_checkpoint without needing their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states an explicit trigger ('when the user wants to resume a different or older session') and names the follow-up alternative with its parameter ('load one with load_session_checkpoint's `checkpoint`'). The discovery-to-load workflow is spelled out rather than inferred.

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