// SCAN REPORT

Reporecall

30 tools. 7 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

7 can modify or destroy data

23 read-only

30 tools total

Community server · catalogue entry verified 11/06/2026

How to control Reporecall ↓

TOOL MAP

Read (23) Write / Execute (4) Destructive / Financial (3)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High clear_index The tool permanently removes indexed data that is central to the server's function of providing code context and intelligence. Destructive · High clear_working_memory This tool irreversibly removes/clears working memory entries from the local store. Destructive · High forget_memory This tool permanently deletes stored memory data and associated index entries without apparent undo capability. Execute · High index_codebase This tool triggers an active operation over the entire codebase — scanning, parsing, and indexing files — and may also regenerate wiki/business pages.

7 of Reporecall's 30 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL REPORECALL

PolicyLayer is an MCP gateway — it sits between your AI agents and Reporecall, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_index": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "compact_memories": {
    "limits": [
      {
        "counter": "compact_memories_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "build_stack_tree": {
    "limits": [
      {
        "counter": "build_stack_tree_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Reporecall — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON REPORECALL →

Free to start. No card required.

ALL 30 REPORECALL TOOLS

DESTRUCTIVE 3 tools

Destructive clear_index Clear all indexed data Destructive clear_working_memory Clear generated working memory entries from the local managed store. Destructive forget_memory Delete a memory by name. Removes the file and its index entries.

EXECUTE 1 tools

Execute index_codebase Index or re-index the codebase. Also regenerates deterministic wiki/business pages when the wiki layer is enab

WRITE 3 tools

Write compact_memories Refresh and compact memory indexes. Falls back to a safe refresh if the compactor is not available. Write store_memory Create or update a memory file. The memory will be indexed for future recall. Write wiki_write Create or update a wiki page manually. Use this to persist codebase knowledge that should be available in futu

READ 23 tools

Read build_stack_tree Build a bidirectional call tree from a seed function/method. Shows callers (who invokes it) and callees (what Read business_context_query Find product areas and business capability pages relevant to a query. Returns business-facing context plus sup Read explain_flow Explain the call flow around a query or function name. Resolves a seed symbol, builds a bidirectional call tre Read explain_memory Explain how memory recall would behave for a query, including selected memories, dropped memories, route, and Read find_callees Find functions called by a given function Read find_callers Find functions that call a given function Read get_communities Get detected code communities (clusters of tightly-coupled modules). Returns community IDs, member counts, coh Read get_hub_nodes Get the most connected nodes (god nodes / architectural hubs) in the call graph. These are functions or classe Read get_imports Get import statements for a file. Shows what modules/symbols a file imports. Read get_lens_data Return current Reporecall Lens JSON from the existing index. Read-only; call refresh_context first when fresh Read get_stats Get index statistics, conventions, and latency info Read get_surprises Get surprising cross-module connections in the codebase — edges that bridge structurally distant communities, Read get_symbol Look up code symbols (functions, classes, methods) by name. Returns matching chunks with file path, lines, and Read list_memories List all stored memories with metadata. Optionally filter by type. Read list_product_areas List product-area aggregates inferred from business wiki pages. Use this for business-facing navigation before Read recall_memories Search project and user memories using local keyword retrieval. Returns relevant memories from prior sessions. Read refresh_context Refresh Reporecall context for external tools: re-index code, regenerate deterministic wiki/business pages whe Read search_code Search the codebase using hybrid vector + keyword search Read suggest_investigations Get suggested investigation questions based on codebase topology — weak resolution edges, bridge nodes, hub no Read wiki_check_staleness Check if wiki pages are stale (referenced files changed since page was written). Optionally check a specific p Read wiki_query Search wiki pages by keyword. Returns matching wiki pages with summaries. Use this to find existing codebase k Read wiki_read Read a wiki page by name, or list all wiki pages if no name is given. Read resolve_seed Resolve a query to seed candidates for stack tree building. Returns ranked code symbols that best match the qu

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Reporecall MCP server? +

Yes. The Reporecall server exposes 3 destructive tools including clear_index, clear_working_memory, forget_memory. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Reporecall? +

The Reporecall server has 3 write tools including compact_memories, store_memory, wiki_write. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Reporecall.

How many tools does the Reporecall MCP server expose? +

30 tools across 4 categories: Destructive, Execute, Read, Write. 23 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Reporecall? +

Register the Reporecall MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Reporecall tool call.

Deterministic rules across all 30 Reporecall tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON REPORECALL →

Free to start. No card required.

30 Reporecall tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Reporecall

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL REPORECALL

// ALL 30 REPORECALL TOOLS

// RELATED SERVERS

// FAQ