SEC failures-to-deliver for a ticker, plus current Reg SHO threshold-list status. Threshold inclusion = >10,000 shares AND >0.5% of total shares outstanding failed for 5 consecutive settlement days. Stratmann-Welborn (2016) document negative drift on threshold-list addition. Returns FTD share cou...
Part of the Openinsider MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call failures_to_deliver to retrieve information from Openinsider without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though failures_to_deliver only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
failures_to_deliver:
rules:
- action: allowSee the full Openinsider policy for all 16 tools.
Agents calling read-class tools like failures_to_deliver have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
SEC failures-to-deliver for a ticker, plus current Reg SHO threshold-list status. Threshold inclusion = >10,000 shares AND >0.5% of total shares outstanding failed for 5 consecutive settlement days. Stratmann-Welborn (2016) document negative drift on threshold-list addition. Returns FTD share count + dollar value per period and a boolean threshold flag. Use when: - User asks 'is TICKER on the threshold list' or 'is there delivery pressure' - Investigating squeeze setups (high SI + threshold-list = stronger composite) - Researching microcap stocks with unusual short-side activity Caveats: ETF FTDs are largely market-maker operational (interpret cautiously); post-T+1 settlement (May 2024), aggregate FTD volumes have decreased materially.. It is categorised as a Read tool in the Openinsider MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for failures_to_deliver. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Openinsider MCP server.
failures_to_deliver 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 failures_to_deliver rule in your Intercept 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 Intercept policy for failures_to_deliver. 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.
failures_to_deliver is provided by the Openinsider MCP server (openinsider-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.