update_sprint_item
[SUPPORT] Edit fields on an existing sprint item: title, version, notes, human_id (assignee), group, deferred_until (enforced deferral), track, or depends_on (dependency ordering). Only the fields you pass are changed; omitted fields are left untouched. Pass an empty string for human_id, group, d...
This record as markdown: /tools/io-github-ajc3xc-meridian/update-sprint-item.md
What update_sprint_item does on Meridian
AI agents use update_sprint_item 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 |
|---|---|---|---|
wave | string | — | 58a45b92 — set/clear the stored wave label (e.g. 'wave-1') for enforced parallel-batch grouping. Hand-override of what assign_sprint_waves computes. Pass an emp |
group | string | — | Objective name to group the item under (item_group); empty string clears it. |
notes | string | — | Free-form note/context shown on the item. |
title | string | — | New title. |
track | string | — | dec69708 — named lane (e.g. 'paper'). Pass an empty string to clear; omit to leave unchanged. |
policy | object | — | 2f9cb288 — per-item override of how strictly a missing/wrong artifact output pointer is enforced. Absent (omit, or on update_sprint_item pass null to clear) fal |
item_id | string | Yes | |
version | string | — | Move the item to a different version/sprint bucket. |
human_id | string | — | Reassign to a person (assignee); empty string clears it. |
priority | string | — | e08fee30 — set the item's priority (urgent|high|normal|low). Higher-priority pending items are surfaced/claimed/grouped first. Omit to leave unchanged. |
depends_on | string | — | 56f607ec — set/fix another sprint item's id this one depends on (must complete first before this item is claimable/surfaced by get_parallelizable_groups). Previ |
project_id | string | — |
Parameters from the server's own tool schema.
Why update_sprint_item is rated Medium
An AI agent can call update_sprint_item faster than any human can review: one bad instruction and it creates or modifies resources in Meridian by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (41 properties)
Attacks that exploit this kind of access
The rule that runs update_sprint_item 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 update_sprint_item, this is the rule to start with:
update_sprint_item 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 update_sprint_item call is checked against it from then on.
Questions about update_sprint_item
[SUPPORT] Edit fields on an existing sprint item: title, version, notes, human_id (assignee), group, deferred_until (enforced deferral), track, or depends_on (dependency ordering). Only the fields you pass are changed; omitted fields are left untouched. Pass an empty string for human_id, group, deferred_until, track, or depends_on to clear it. Returns the updated item, or an error if the id is unknown. For TWO OR MORE independent item patches, prefer the single execute_batch(operation='item_updates', entries=[...], mode='best_effort' or 'all_or_nothing', idempotency_key='...') call instead of repeating this tool: it validates and reports each item in input order, supports per-item correlation_key values, and makes retries idempotent. Use best_effort when one invalid item must not block the rest; use all_or_nothing when the whole patch set must succeed together. 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.
update_sprint_item accepts 12 parameters: wave, group, notes, title, track, policy, item_id, version, human_id, priority, depends_on, project_id. Required: item_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 update_sprint_item: 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.
update_sprint_item 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 update_sprint_item 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 update_sprint_item. 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.
update_sprint_item 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