fbi-crime-mcp-server

FBI Get LEOKA

fbi_get_leoka

Read-onlyIdempotent

LEOKA officer fatality trends, weapons, activity, circumstances, demographics, geographic regions, and time-of-day/month breakdowns, 2020 through the current year. Period "ytd" requests a year; "monthly" requires month and includes the same month of the comparison year. Both periods return the CDE YTD totals block, separately from month-specific breakdowns. Raw dod/doi totals have unspecified interpretation; classified deaths remain in the trend and region series.

Input Schema

Name	Required	Description
`year`	Yes	Year to retrieve LEOKA data for, 2020 through the current year. Required — the API does not default to a year.
`month`	No	Month number (1–12). Required for monthly; must be omitted for YTD.
`period`	Yes	Data period: ytd for the year, monthly for month-specific breakdowns and comparison years. Both include the CDE YTD totals block.

Output Schema

Name	Required	Description
`year`	No	The data year requested.
`error`	No	Present when the call failed. Absent on success.
`month`	No	The data month, when period is "monthly".
`period`	No	The requested data period.
`totals`	No	Raw incidents_victim_officer_totals_ytd block, including in monthly responses. Not combined fatalities or requested-month totals.
`weapons`	No	Count by weapon type (e.g. Handguns, Rifles, Vehicle).
`deaths_by_year`	No	Annual officer death totals by type over the window CDE returns, which can include years after the requested one (YTD 2023 returns 2018–2026); the current year's entry is year-to-date. Keys: "Felonious", "Accidental". Values: { "2022": 61, ... }
`body_armor_worn`	No	Body armor worn category to count; null counts are unavailable.
`deaths_by_region`	No	Officer death counts by killing type then region. Keys: "Felonious", "Accidental". Values: { "South": 31, "West": 12, ... }
`officer_activity`	No	Count by what the officer was doing at the time of the incident.
`location_of_attack`	No	Location of attack category to count; all reported categories are retained.
`weather_conditions`	No	Weather condition to count.
`lighting_conditions`	No	Count by lighting conditions at time of incident.
`officer_demographic`	No	Officer demographic dimension to category to count; null groups and counts are unavailable.
`offender_demographic`	No	Offender demographic dimension to category to count; null groups and counts are unavailable.
`officer_incident_type`	No	Officer incident type to count.
`officer_death_by_month`	No	Killing type to year to month to count, for the requested year and the comparison year CDE returns. Only months CDE covers are present: monthly responses hold the requested month under each year, current-year YTD responses hold months through the current UTC month, and past-year YTD responses keep the series as returned. Zeros are reported counts; null means unavailable.
`officer_type_of_assignment`	No	Officer assignment type to count.
`offender_prior_relationship`	No	Offender prior relationship category to count.
`officer_death_by_time_of_day`	No	Killing type to hour key to count. Hour keys, including -1, are preserved literally.
`offender_prior_mental_illness`	No	Offender prior mental illness category to count.
`offender_previously_known_to_agency`	No	Previously known offender category to count.
`officer_circumstances_time_of_attack`	No	Circumstance at time of attack category to count.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 23, 2026

changedInput schema / properties / year / description

Previous value: -"Year to retrieve LEOKA data for. Required — the API does not default to a year."New value: +"Year to retrieve LEOKA data for, 2020 through the current year. Required — the API does not default to a year."

changedInput schema / properties / year / maximum

Previous value: -2030New value: +9007199254740991

changedInput schema / properties / year / minimum
```
Previous value: -2000New value: +2020
```

changedOutput schema / properties / deaths_by_year / description

Previous value: -"Annual officer death totals by type. Keys: \"Felonious\", \"Accidental\". Values: { \"2022\": 61, ... }"New value: +"Annual officer death totals by type over the window CDE returns, which can include years after the requested one (YTD 2023 returns 2018–2026); the current year's entry is year-to-date. Keys: \"Felonious\", \"Accidental\". Values: { \"2022\": 61, ... }"

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `month_not_applicable`: period is \"ytd\" but a month was supplied. `month_required`: period is \"monthly\" but the month parameter was not provided. `no_data`: The API returned no LEOKA data for the requested year/month. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `month_not_applicable`: period is \"ytd\" but a month was supplied. `month_required`: period is \"monthly\" but the month parameter was not provided. `year_out_of_range`: year is after the current UTC year. `no_data`: The API returned no LEOKA data for the requested year/month. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "month_not_applicable",
-  "month_required",
-  "no_data"
-]New value: +[
+  "month_not_applicable",
+  "month_required",
+  "year_out_of_range",
+  "no_data"
+]

changedOutput schema / properties / officer_death_by_month / description

Previous value: -"Killing type to year to month to count. Includes returned comparison years and zero values without filtering."New value: +"Killing type to year to month to count, for the requested year and the comparison year CDE returns. Only months CDE covers are present: monthly responses hold the requested month under each year, current-year YTD responses hold months through the current UTC month, and past-year YTD responses keep the series as returned. Zeros are reported counts; null means unavailable."

First observedOct 13, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, open-world behavior. The description adds meaningful data caveats: both periods return a CDE YTD totals block separately from month-specific breakdowns, raw dod/doi totals have unspecified interpretation, and classified deaths remain in the trend/region series. These are useful behavioral disclosures beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded with the resource scope, then period semantics, then data caveats. Every sentence contributes useful information, though the long opening sentence could be slightly more scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return values. It covers the key caller-facing concerns: supported time range, period/month interaction, comparison-year behavior, and caveats about dod/doi and classified deaths. It is largely complete for a three-parameter analytical tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes further by clarifying the relational semantics of period and month: monthly includes the same month of the comparison year, and both periods return the CDE YTD totals block. This adds value beyond the schema's per-field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as LEOKA officer fatality data and enumerates the included dimensions (trends, weapons, activity, circumstances, demographics, regions, time breakdowns). It does not explicitly differentiate itself from sibling FBI tools such as fbi_get_arrests or fbi_get_hate_crimes, but the subject matter is specific enough to distinguish it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains how the period parameter works ('ytd' requests a year; 'monthly' requires month and includes comparison-year data), which gives operational guidance. However, it does not state when to choose this tool over alternative FBI datasets or any exclusions/preconditions beyond period mechanics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All fbi-crime-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.