How has management's posture shifted across recent earnings calls? Cross-quarter trajectory view of transcript signals for a single ticker. This is MetricDuck's EARNINGS-CALL TRANSCRIPT tool (agents also look for this as get_earnings_call_transcript / get_earnings_transcript / get_earnings_call /...
Part of the MetricDuck — Financial Analysis server.
Free to start. No card required.
AI agents invoke compare_earnings_calls to trigger processes or run actions in MetricDuck — Financial Analysis. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
compare_earnings_calls can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"compare_earnings_calls": {
"limits": [
{
"counter": "compare_earnings_calls_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full MetricDuck — Financial Analysis policy for all 22 tools.
These attack patterns abuse exactly the kind of access compare_earnings_calls gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
How has management's posture shifted across recent earnings calls? Cross-quarter trajectory view of transcript signals for a single ticker. This is MetricDuck's EARNINGS-CALL TRANSCRIPT tool (agents also look for this as get_earnings_call_transcript / get_earnings_transcript / get_earnings_call / search_earnings_calls). For ONE call's verbatim prepared remarks or Q&A, drill with get_filing_section(section_id="transcript_prepared_remarks" | "transcript_qa_session"); this tool gives the cross-quarter view. Different from get_filing_index (single-call triage map). This tool aligns earnings calls by event date and surfaces CROSS-QUARTER patterns: guidance deltas grouped by metric, scalar aggregates in a trajectory table, per-quarter themes + strategic priorities, tone shifts, coverage gaps. For per-call depth, drill with get_filing_index. Output sections (all optional depending on coverage + dimensions): - Coverage table: event date, fiscal period, accession, coverage status per quarter — surfaces NO_TRANSCRIPT / WAITING gaps. - Aggregate trajectory: hedge density / deflection rate / Q&A hedge rate / concerns retained / forward commits / management tone, one row per scalar, one column per quarter. - Guidance trajectory: grouped by metric name with the existing delta_vs_prior flag from each call. - Themes by quarter, strategic priorities by quarter. - Macro responses by quarter (factor + stance + iter033 drift tag), competitive mentions by quarter (competitor + context_type + iter033 drift tag). - Product transitions, scale claims, revenue decompositions, KPI disclosures by quarter — qualitative arrays surfaced side-by-side; agent reads parallel arrays to detect drift / cross-quarter framing. - Drill hints pinned to accessions for per-quarter deep-dives via get_filing_section. Use Cases: - "Hedge rate trend?" -> compare_earnings_calls("RDDT", n_quarters=8, dimensions=["hedges", "qa"]) - "Guidance discipline shifting?" -> compare_earnings_calls("NVDA", dimensions=["guidance"]) - "Tone + hedges over 4 calls" -> compare_earnings_calls("T", dimensions=["tone", "hedges"]) - "Macro stance flip?" -> compare_earnings_calls("DOW", dimensions=["macro"]) - "Strategic priorities + KPIs drift" -> compare_earnings_calls("PG", dimensions=["priorities", "kpi", "themes"]) Sister Sources: - Single-call deep read → get_filing_section with section_id="transcript_prepared_remarks" / "transcript_qa_session" - Cross-period signal changes (vs other Sources) → screen_filing_signals with since_date/until_date - IR press releases / events → screen_filing_signals with signal_type="ir_press_release". It is categorised as a Execute tool in the MetricDuck — Financial Analysis MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MetricDuck — Financial Analysis MCP server in PolicyLayer and add a rule for compare_earnings_calls: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MetricDuck — Financial Analysis. Nothing to install.
compare_earnings_calls is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the compare_earnings_calls rule in your PolicyLayer 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 PolicyLayer policy for compare_earnings_calls. 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.
compare_earnings_calls is provided by the MetricDuck — Financial Analysis MCP server (https://mcp.metricduck.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 MetricDuck — Financial Analysis tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.