// MCP TOOL REFERENCE

POSTSCRIPT TOOLS

24 tools from the Postscript MCP Server, categorised by risk level.

View the Postscript policy → Token cost: 7,771 tokens →

// ALL 24 POSTSCRIPT TOOLS

READ 17 tools

Read ai_visibility_check Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (... Read ask_pipeworx PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS... Read bet_research Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("wi... Read compare_entities "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank... Read entity_profile "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Mic... Read pipeworx_feedback Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale... Read pipeworx_trending What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call vo... Read polymarket_arbitrage Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. TWO MODES: (... Read polymarket_kalshi_spread Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes ... Read postscript_get_keyword Get a single SMS keyword by its ID. Returns the keyword text, status, and configuration (welcome message, l... Read postscript_get_subscriber Get a single SMS subscriber by Postscript subscriber ID. Returns phone number, email, subscription status, ... Read postscript_list_keywords List all active SMS keywords for the shop. Keywords are the text-to-join words (e.g. "JOIN") subscribers te... Read postscript_list_subscribers List SMS subscribers for a Postscript (Shopify) shop. Supports filtering by email, phone number, Shopify cu... Read recent_changes "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" ... Read scan_competitor_ai_presence Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors... Read scan_dependency Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (licen... Read validate_claim "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confi...

WRITE 3 tools

Write discover_tools Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what t... Write generate_llms_txt Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can inde... Write resolve_entity "What's the ticker for…" / "find the CIK for…" / "what's the RxCUI for…" / "look up the ID for…" / "what is...

DESTRUCTIVE 4 tools

Destructive forget Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear... Destructive polymarket_edges Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built... Destructive recall Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look... Destructive remember Save data the agent will need to reuse later — across this conversation or across sessions. Use when you di...

// FAQ

How many tools does the Postscript MCP server have? +

The Postscript MCP server exposes 24 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Postscript tools? +

Route the Postscript server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Postscript tools fall into? +

Postscript tools are categorised as Read (17), Write (3), Destructive (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.