audit_project_articles
Audit ALL articles across a whole project in a single paginated call, plus counts by status — instead of calling list_articles once per site (which is slow at 100+ sites). Returns a slim summary per article (siteId, title, slug, status, targetKeyword, dates); no body. Filter by status / updatedSi...
This record as markdown: /tools/a3plus-mcp/audit-project-articles.md
What audit_project_articles does on A3plus
AI agents call audit_project_articles to retrieve information from A3plus without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Page size 1-500, default 200. |
offset | number | — | Pagination offset, default 0. |
status | string | — | Optional status filter. |
projectId | string | Yes | The A3Plus project ID. Required unless A3PLUS_PROJECT_ID env var is set. |
updatedSince | string | — | ISO timestamp — only articles updated on/after this. |
includeDrafts | boolean | — | Default true. Set false to return only published. |
Parameters from the server's own tool schema.
Why audit_project_articles is rated Low
Even though audit_project_articles only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs audit_project_articles safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For audit_project_articles, this is the rule to start with:
audit_project_articles is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every audit_project_articles call is checked against it from then on.
Questions about audit_project_articles
Audit ALL articles across a whole project in a single paginated call, plus counts by status — instead of calling list_articles once per site (which is slow at 100+ sites). Returns a slim summary per article (siteId, title, slug, status, targetKeyword, dates); no body. Filter by status / updatedSince. It is categorised as a Read tool in the A3plus MCP Server, which means it retrieves data without modifying state.
audit_project_articles accepts 6 parameters: limit, offset, status, projectId, updatedSince, includeDrafts. Required: projectId. The full parameter table on this page comes from the server's own tool schema.
Register the A3plus MCP server in PolicyLayer and add a rule for audit_project_articles: 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 A3plus. Nothing to install.
audit_project_articles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the audit_project_articles 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 audit_project_articles. 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.
audit_project_articles is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A3plus, and thousands of servers like it.
This server
Across the catalogue