checkpoint
[SUPPORT] Save progress mid-session. Runs auto_capture (buckets done tasks into a note), generates a delta handoff, and returns a compact summary with what was done, what's pending, and the suggested next /goal string (now the same canonical, token-embedded continuation block generate_handoff ren...
This record as markdown: /tools/io-github-ajc3xc-meridian/checkpoint.md
What checkpoint does on Meridian
AI agents call checkpoint to permanently remove resources in Meridian, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
version | string | — | (455cfc36) Optional explicit sprint-version bucket (e.g. 'v0.2.6') to scope this checkpoint to — wins over the calling session's own stored sprint_version, exac |
project_id | string | — | |
session_id | string | Yes | |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
Parameters from the server's own tool schema.
Why checkpoint is rated Critical
An AI agent that decides to call checkpoint doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Meridian is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs checkpoint safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For checkpoint, this is the rule to start with:
checkpoint is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every checkpoint call is checked against it from then on.
Questions about checkpoint
[SUPPORT] Save progress mid-session. Runs auto_capture (buckets done tasks into a note), generates a delta handoff, and returns a compact summary with what was done, what's pending, and the suggested next /goal string (now the same canonical, token-embedded continuation block generate_handoff renders — verify it with verify_handoff_token exactly like any other /goal block). Call before context fills up or before ending a session. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata -- including task log entries, pinned decisions, sprint items, notes, handoff/goal state, and HITL queue items -- are sent to and stored in Meridian's service, in an isolated per-tenant Postgres database (Neon); self-hosted deployments keep the same categories in the configured local SQLite/Postgres database. This data is visible in the dashboard and API, and may resurface in later project context or handoffs. Notes and pinned decisions can be deleted individually; task log entries and sprint items can be deleted via the dashboard/API (not exposed as an agent-facing tool); HITL queue items and handoff state have no per-record delete. Full removal of any of this data is available via project or account deletion, using the documented controls. Do not include secrets. It is categorised as a Destructive tool in the Meridian MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
checkpoint accepts 4 parameters: version, project_id, session_id, project_name. Required: session_id. The full parameter table on this page comes from the server's own tool schema.
Register the Meridian MCP server in PolicyLayer and add a rule for checkpoint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meridian. Nothing to install.
checkpoint is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the checkpoint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for checkpoint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
checkpoint is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meridian, and thousands of servers like it.
Across the catalogue