start_wave_run
[SUPPORT] 2a654cb0 — DURABLE WAVE STATE: open a wave run before dispatching a parallel wave. Returns an immutable wave_run_id pinned to the canonical expanded board snapshot (revision_hash + monotonic revision_counter) the wave was planned against, so a session that dies mid-wave can be resumed a...
This record as markdown: /tools/io-github-ajc3xc-meridian/start-wave-run.md
What start_wave_run does on Meridian
AI agents use start_wave_run to create or update resources in Meridian, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meridian environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
actor | string | — | Optional session_id or actor name recorded as opening the run. |
version | string | — | Optional sprint-version bucket this wave covers. Scopes the pinned board snapshot to that bucket. |
item_ids | array | — | Sprint item ids in this wave. Registered as children in status='running'. |
project_id | string | — | |
wave_label | string | — | Optional label for the wave, e.g. 'wave-2'. |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
failure_modes | object | — | Optional {item_id: 'stop'|'continue'}. A 'stop' child that later fails blocks finalization. Unlisted items default to 'continue'. |
degraded_tools | array | — | Optional [{tool, reason, fallback}] provenance for tools unavailable during this wave (e.g. Serena tunnel inactive). |
Parameters from the server's own tool schema.
Why start_wave_run is rated Medium
This tool creates a durable wave run record on the server side, pinning a snapshot and registering sprint items. It is a Write operation — it creates a new persistent entity (wave_run_id with associated state) but does not delete data or execute code/commands. Severity is medium because misuse could corrupt task coordination state across parallel AI coding sessions, but it does not irreversibly destroy data.
From the tool's definition open a wave run before dispatching a parallel wave. Returns an immutable wave_run_id pinned to the canonical expanded board snapshot
Attacks that exploit this kind of access
The rule that runs start_wave_run 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 start_wave_run, this is the rule to start with:
start_wave_run stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every start_wave_run call is checked against it from then on.
Questions about start_wave_run
[SUPPORT] 2a654cb0 — DURABLE WAVE STATE: open a wave run before dispatching a parallel wave. Returns an immutable wave_run_id pinned to the canonical expanded board snapshot (revision_hash + monotonic revision_counter) the wave was planned against, so a session that dies mid-wave can be resumed against a manifest whose staleness is DETECTABLE instead of assumed. The snapshot is built server-side — you cannot supply one, because the point is to pin what the server saw. Pass item_ids (the sprint items in this wave) and optionally failure_modes ({item_id: 'stop'|'continue'}) to register them as children up front: a failed 'stop' child then structurally BLOCKS finalize_wave_run. degraded_tools ([{tool, reason, fallback}]) records which tools were unavailable while the wave ran, so a later reader knows the evidence quality. Returns {wave_run_id, run, children, revision_hash, revision_counter}. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the dashboard/API and later project context or handoffs. Delete individual tasks, notes, or decisions where supported, or delete the project/account using the documented controls. Do not include secrets. It is categorised as a Write tool in the Meridian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
start_wave_run accepts 8 parameters: actor, version, item_ids, project_id, wave_label, project_name, failure_modes, degraded_tools. 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 start_wave_run: 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.
start_wave_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the start_wave_run 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 start_wave_run. 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.
start_wave_run 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.
This server
Across the catalogue