Retrieve complete details for a specific newsletter post by its unique slug identifier. Returns formatted markdown with all post metadata and content. The response is formatted as markdown with sections for: - Post title and basic metadata (slug, status, category, author(s), dates) - Summary/shor...
AI agents call get_newsletter_post to retrieve information from Langfuse Observability without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a data retrieval operation on an existing newsletter post identified by a slug. It returns information without creating, modifying, deleting, or executing any operations. The tool has no side effects and does not alter state. Even if an AI agent misuses it by requesting posts it shouldn't access, the blast radius is limited to information disclosure, classified as low severity.
From the tool's definition Tool description states it 'Retrieve[s] complete details for a specific newsletter post' and 'Returns formatted markdown with all post metadata and content.' The verb 'retrieve' and the read-only nature of fetching existing post data with no modification…
Attacks that exploit this kind of access
Retrieve complete details for a specific newsletter post by its unique slug identifier. Returns formatted markdown with all post metadata and content. The response is formatted as markdown with sections for: - Post title and basic metadata (slug, status, category, author(s), dates) - Summary/short description - Full HTML content (body field) as raw HTML - Complete metadata including all URLs, SEO tags, and featured items - Table of contents (if available) as raw HTML All available fields from the post are included: - title, slug, status, category - authors (ordered list; the primary author is listed first) - created_at, updated_at, last_updated - short_title, short_description - body (raw HTML content) - table_of_contents (raw HTML) - image_url, preview_image_url, share_image - title_tag, description_tag - featured_mcp_server_ids, featured_mcp_client_ids Status meanings: - draft: Unpublished posts that are being written or edited - live: Published posts visible on the website Use cases: - View the complete content of a specific newsletter post - Check the current status and metadata of a post before editing - Retrieve SEO fields for optimization or analysis - Get the full HTML content for preview or export - Review featured MCP servers and clients associated with a post - Verify author information and timestamps. It is categorised as a Read tool in the Langfuse Observability MCP Server, which means it retrieves data without modifying state.
Register the Langfuse Observability MCP server in PolicyLayer and add a rule for get_newsletter_post: 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 Langfuse Observability. Nothing to install.
get_newsletter_post 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 get_newsletter_post 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 get_newsletter_post. 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.
get_newsletter_post is provided by the Langfuse Observability MCP server (langfuse-observability-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →