Create or update one OrgX record (snake_case fields). Create needs: initiative title; workstream title+initiative_id; milestone title+workstream_id; task title+workstream_id; decision title; blocker run_id+description in metadata; skill/studio records title. Artifacts need entity_type+entity_id (...
AI agents use orgx_write to create or update resources in OrgX — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OrgX environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | — | REQUIRED when operation="update". Target entity UUID to patch. |
name | string | — | Alternative to "title" on create. REQUIRED on create when "title" is not provided. |
type | string | — | Entity type to write: task, milestone, decision, artifact, skill, blocker, studio_brand, studio_content, initiative, workstream, or objective. See top-level des |
title | string | — | REQUIRED on create (provide either "title" or "name" — they are aliases). Display title of the new entity. |
fields | object | — | REQUIRED when operation="update". Map of entity fields to patch (only include fields you want to change). |
run_id | string | — | REQUIRED when type="blocker". Agent run UUID the blocker applies to. |
status | string | — | Initial workflow status; common agent aliases such as "active" are normalized per entity type ("active" → "in_progress"). |
step_id | string | — | Optional agent run step UUID for blocker creation. |
summary | string | — | Short description shown in lists and previews. Recommended on create. |
task_id | string | — | Shortcut for attaching an artifact directly to a task. Use instead of entity_type+entity_id when type="artifact" and the target is a task. |
_context | object | — | Client context for conversation tracking (strongly recommended for cross-client continuity) |
due_date | string | — | Due date as YYYY-MM-DD. |
Parameters from the server's own tool schema.
An AI agent can call orgx_write faster than any human can review — one bad instruction and it creates or modifies resources in OrgX by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (50 properties)
Documented attack patterns abuse exactly the kind of access orgx_write gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OrgX, and nothing reaches the server without passing your rules. This is the rule we recommend for orgx_write:
{
"version": "1",
"default": "deny",
"tools": {
"orgx_write": {
"limits": [
{
"counter": "orgx_write_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}orgx_write 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.
Free to start. No card required.
Create or update one OrgX record (snake_case fields). Create needs: initiative title; workstream title+initiative_id; milestone title+workstream_id; task title+workstream_id; decision title; blocker run_id+description in metadata; skill/studio records title. Artifacts need entity_type+entity_id (or task_id), artifact_type, and artifact_url|external_url|preview_markdown. Practical founder/team artifact examples: orchestration.next_initiative, eng.pull_request, eng.deploy_proof, eng.structured_blocker, sales.strategy, sales.icp_offer_sequence, sales.send_plan, marketing.launch_asset, marketing.channel_hypothesis, product.customer_discovery, product.prd, product.pricing_hypothesis, product.decision_record, design.audit, design.component_spec, design.token_package, ops.operator_brief, ops.runbook, ops.budget_envelope, ops.incident_status, proof.link. Update REQUIRES id + fields patch. Priority/due_date/status aliases normalize server-side. USE WHEN: adding or editing durable OrgX records. NEXT: orgx_act to launch/complete records, or orgx_submit_receipt when the write is completion proof. DO NOT USE for lifecycle state changes or artifact-only proof; use orgx_act or orgx_attach. It is categorised as a Write tool in the OrgX MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
orgx_write accepts 12 parameters: id, name, type, title, fields, run_id, status, step_id, summary, task_id, _context, due_date. The full parameter table on this page comes from the server's own tool schema.
Register the OrgX MCP server in PolicyLayer and add a rule for orgx_write: 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 OrgX. Nothing to install.
orgx_write 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 orgx_write 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 orgx_write. 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.
orgx_write is provided by the OrgX MCP server (useorgx/orgx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 OrgX tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
29 OrgX tools catalogued and risk-classified — across an index of 42,500+ MCP servers.