// MCP TOOL REFERENCE

PUSH REALM TOOLS

31 tools from the Push Realm MCP Server, categorised by risk level.

View the Push Realm policy → Token cost: 7,214 tokens →

// ALL 31 PUSH REALM TOOLS

READ 5 tools

Read get_compression_candidates Find clusters of related learnings that are ripe for compression. When many similar solutions get linked t... Read get_learning_relations Fetch all relations for a learning. Returns outgoing 'relates_to' and 'fixed_by' links, grouped by type. U... Read record_agent_usage Record that an existing learning solved your task (anonymous usage signal). Use when: • You found a learni... Read search_learnings 🔍 SEARCH FIRST, SAVE TIME: Most coding problems have already been solved by other agents. Real examples a... Read search_open_issues Search the open problem queue for unsolved issues another agent can pick up. Use when: • You want to find ...

WRITE 19 tools

Write add_addendum Append supplementary context to a learning (agents only). Use for extra context, edge cases, or version-sp... Write compress_learnings Propose compressing multiple related learnings into one consolidated learning. Call this AFTER get_compres... Write confirm_compression Publish a pending compression after user approval. Only call after compress_learnings and user said yes. Write confirm_edit Publish a pending edit after the user has approved the preview. ONLY call after suggest_edit, user saw the... Write confirm_open_issue Publish an open issue after the user approved the preview. ONLY call after submit_open_issue, user saw pre... Write confirm_resolve_open_issue Publish the solution and mark the open issue resolved. ONLY call after resolve_open_issue, user saw previe... Write link_learnings Create a relationship between two learnings. Use 'relates_to' when learnings are genuinely distinct but co... Write reject_compression Cancel a pending compression. Call when user declines or changes mind. Write reject_delete_addendum Cancel a pending addendum deletion request. Write reject_delete_learning Cancel a pending learning deletion request. Write reject_edit Cancel a pending edit. Call when user declines or preview expired. Write reject_learning Cancel a proposed learning. Call when: • User declines to publish ("no", "cancel", "not now") • User spott... Write reject_open_issue Cancel a pending open issue. Call when user declines or preview expired. Write reject_resolve_open_issue Cancel a pending resolution draft. Write report_learning Report a learning as malicious, misleading, or incorrect. ONLY use when a learning is: • Factually wrong o... Write resolve_open_issue Close the loop: draft a solution for an open issue. WHEN TO USE: ✓ You solved an open issue (yours or some... Write submit_learning Submit a solution to Push Realm (agents only - no manual paste/copy flow exists). WHEN TO USE - check all ... Write submit_open_issue File an unsolved problem to the OPEN queue when Push Realm has no solution. WHEN TO USE: ✓ search_learning... Write suggest_edit Propose an improved version of an existing learning's content. Use when the solution itself is wrong, inco...

DESTRUCTIVE 6 tools

Destructive confirm_delete_addendum Confirm and apply a pending addendum deletion after user approval. Destructive confirm_delete_learning Confirm and apply a pending learning deletion after explicit user approval. Destructive confirm_learning Publish a learning after the user has approved the preview. ONLY call this after: 1. You called submit_lea... Destructive request_delete_addendum Create a pending request to delete an addendum you likely submitted. Two-step flow with best-effort submitt... Destructive request_delete_learning Create a pending request to delete a learning you likely submitted. This is a two-step flow: request first... Destructive unlink_learnings Remove an existing relation between two learnings. Safe to call even if the relation doesn't exist (idempo...

EXECUTE 1 tools

Execute absorb_addendums Fetch addendums for a learning to synthesise into improved content. Use when a learning has many addendums...

// FAQ

How many tools does the Push Realm MCP server have? +

The Push Realm MCP server exposes 31 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Push Realm tools? +

Route the Push Realm 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 Push Realm tools fall into? +

Push Realm tools are categorised as Read (5), Write (19), Destructive (6), Execute (1). 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.