// SCAN REPORT

Openinsider

16 tools. 2 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 6 May 2026

2 can modify or destroy data

14 read-only

16 tools total

// TOOL MAP

Read (14) Write / Execute (1) Destructive / Financial (1)

// WHAT CAN GO WRONG

Destructive tools (dilution_filings) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Execute tools (screen) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

// RECOMMENDED RULES

Deny destructive operations

dilution_filings:
  rules:
    - action: deny

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

Cap read operations

activist_filings:
  rules:
    - rate_limit: 60/minute

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

// ALL 16 OPENINSIDER TOOLS

DESTRUCTIVE 1 tools

Destructive dilution_filings

EXECUTE 1 tools

Execute screen

READ 14 tools

Read activist_filings Read cluster_buys Read daily_short_volume Read failures_to_deliver Read get_quote Read late_filings Read latest_trades Read officer_buys Read recent_sec_filings Read search_by_insider Read search_by_ticker Read short_interest Read top_buys Read top_sells

// FAQ

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

Yes. The Openinsider server exposes 1 destructive tools including dilution_filings. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How many tools does the Openinsider MCP server expose? +

16 tools across 3 categories: Destructive, Execute, Read. 14 are read-only. 2 can modify, create, or delete data.

How do I add Intercept to my Openinsider setup? +

One line change. Instead of running the Openinsider server directly, prefix it with Intercept: intercept -c openinsider.yaml -- npx -y @openinsider-mcp. Download a pre-built policy from policylayer.com/policies/openinsider and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

GET STARTED →