timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
FBI Crime Data Explorer — offense rates, hate crime, arrests, NIBRS, LEOKA, staffing, agency search.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 6/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 26/100 |
质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Fbi Crime MCP Server。按照 https://mcp.popnx.com/i/cyanheads-fbi-crime-mcp-server.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 5/5 项检查 · 你的提问会经过开发者的服务器(fbi-crime.caseyjhand.com) · ✓ 命令已检查 2026年11月16日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Fbi Crime MCP Serverhttps://fbi-crime.caseyjhand.com/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsFbi Crime MCP Server
用 Fbi Crime MCP Server 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Fbi Crime MCP Server,或回答中出现 Fbi Crime MCP Server 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Fbi Crime MCP Serverhttps://fbi-crime.caseyjhand.com/mcp开启新聊天,输入前先从插件列表中选择 Fbi Crime MCP Server
用 Fbi Crime MCP Server 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Fbi Crime MCP Server,或回答中出现 Fbi Crime MCP Server 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user fbi-crime https://fbi-crime.caseyjhand.com/mcp应能看到 Fbi Crime MCP Server 在列表中并显示已连接
用 Fbi Crime MCP Server 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Fbi Crime MCP Server,或回答中出现 Fbi Crime MCP Server 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Fbi Crime MCP Server 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Fbi Crime MCP Server,或回答中出现 Fbi Crime MCP Server 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Fbi Crime MCP Server 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Fbi Crime MCP Server,或回答中出现 Fbi Crime MCP Server 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://fbi-crime.caseyjhand.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user fbi-crime https://fbi-crime.caseyjhand.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"fbi-crime": {
"url": "https://fbi-crime.caseyjhand.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"fbi-crime": {
"type": "http",
"url": "https://fbi-crime.caseyjhand.com/mcp"
}
}
}Claude Code
claude mcp add --scope user fbi-crime --env FBI_API_KEY=your-value -- npx -y @cyanheads/fbi-crime-mcp-serverClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"fbi-crime": {
"command": "npx",
"args": [
"-y",
"@cyanheads/fbi-crime-mcp-server"
],
"env": {
"FBI_API_KEY": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"fbi-crime": {
"command": "npx",
"args": [
"-y",
"@cyanheads/fbi-crime-mcp-server"
],
"env": {
"FBI_API_KEY": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"fbi-crime": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/fbi-crime-mcp-server"
],
"env": {
"FBI_API_KEY": "your-value"
}
}
}
}FBI_API_KEY 机密 必填 envFBI_CLAMP_LIMITS envMCP_LOG_LEVEL env说明为自动翻译,变量名保持原样;不确定时请查看原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
工具名称和描述与服务器在 2026年11月19日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
fbi_search_agenciesFind law enforcement agencies in one state and their nine-character ORI codes, the identifier agency scope needs in fbi_get_crime_estimates, fbi_get_hate_crimes, fbi_get_arrests, fbi_get_nibrs_breakdown, and fbi_get_police_employees. Fetches the state's full FBI CDE agency direct
fbi_get_crime_estimatesMonthly offense rates (per 100,000 participating population), raw counts, population denominators and provider reporting coverage from FBI CDE, January 1985 through the current year; current-year months past the latest data return null values. National scope omits identifiers; st
fbi_get_nibrs_breakdownNIBRS incident breakdowns reported to FBI CDE for one offense, for the nation, a state, or an agency, summed over a month window from January 1991 through the current year. Returns victim counts by age, sex, race, location, ethnicity, and relationship to the offender; offender co
fbi_get_arrestsArrest counts reported to FBI CDE for the nation, a state, or an agency, summed over a month window from January 1985 through the current year. Returns arrests by offense name, offense category, and detailed offense breakdown, by arrestee sex and race, and by age group for male a
fbi_get_hate_crimesHate crime counts reported to FBI CDE for the nation, a state, or an agency, summed over a month window from January 1991 through the current year. Returns incidents by bias motivation and bias category, plus counts by offense type, location type, offender race, offender ethnicit
fbi_get_leokaLEOKA 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 peri
fbi_get_police_employeesLaw enforcement staffing reported to FBI CDE for the nation, a state, or an agency, one row per year from 1985 through the current year: male and female sworn officers, male and female civilian employees, law enforcement employees per 1,000 people, the participated population, an
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 cyanheads 验证,该账户拥有此仓库
代码最后更新于4天前
使用 Apache-2.0
在 462 毫秒内响应(HTTP 200)
无需登录
已读取 7 个工具描述,未发现针对 AI 的隐藏指令
云端地址最近 5 次检查中有 5 次响应 · 最近一次 462 ms · 检查于 2026年11月19日
尚未检查
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/cyanheads-fbi-crime-mcp-server)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:FBI_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于4天前,最新版本(0.5.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Fbi Crime MCP Server | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 是 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 5/5 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | Apache-2.0 | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
@cyanheads/fbi-crime-mcp-server Exposes the FBI Crime Data Explorer API — monthly UCR offense rates and counts, hate crime, arrest, and NIBRS breakdowns by national, state, or agency scope, agency ORI search, annual law enforcement staffing, and LEOKA officer-safety statistics via MCP. STDIO or Streamable HTTP. 7 Callable Tools • 5 Disabled Tools • 0 Registered Resources • 1 Skill
Public Hosted Server: https://fbi-crime.caseyjhand.com/mcp
US crime statistics from the FBI Crime Data Explorer: monthly offense rates and counts with population and reporting coverage, hate crime, arrest, and NIBRS totals at the national, state, or agency level, agency ORI search by state, annual law enforcement staffing (sworn officers and civilians), and statistics on law enforcement officers killed and assaulted (LEOKA).
| Tool | Description |
|---|---|
fbi_search_agencies | Find agencies in one state and their ORI codes from the CDE agency directory; filter by name words, county, and agency type; paged |
fbi_get_crime_estimates | Monthly UCR offense rates and counts by national, state, or agency scope, from the CDE summarized endpoint; optional state and national comparison rates |
fbi_get_hate_crimes | Hate crime incidents by bias motivation and category, plus offense, location, offender, and judicial-district breakdowns, 1991 through the current year; opt-in monthly counts, rates, and reporting coverage |
fbi_get_arrests | Arrest counts by offense, arrestee sex and race, and age group, 1985 through the current year; opt-in monthly counts, rates, and reporting coverage |
fbi_get_nibrs_breakdown | NIBRS victim, offender, weapon, and related-offense breakdowns for one offense, 1991 through the current year; opt-in monthly offense and clearance counts, rates, and reporting coverage |
fbi_get_leoka | Officer fatality, weapon, and circumstance data (LEOKA) by month or year-to-date, 2020 through the current year |
fbi_get_police_employees | Annual law enforcement staffing (sworn officers and civilians by sex, employees per 1,000 people, participated population) by national, state, or agency scope, 1985 through the current year |
fbi_get_arson | [DISABLED] Use fbi_get_crime_estimates with offense="arson" |
fbi_get_agency | [DISABLED] UCR agency profile backend decommissioned; use fbi_search_agencies |
fbi_get_human_trafficking | [DISABLED] UCR human trafficking backend decommissioned |
fbi_get_participation | [DISABLED] UCR and CDE participation backends decommissioned |
fbi_list_code_table | [DISABLED] UCR code table backend decommissioned |
The five unavailable entries above are disabled operator records, not callable tools. Visit FBI CDE for retired datasets.
| Skill | Description |
|---|---|
fbi-crime-guide | Gates the tool descriptions don't carry: where an agency ORI comes from, an unrecognized state or ORI versus one that reported nothing, null versus zero, which category map holds a headline total, and reporting coverage before comparing periods |
Plugin installs load it from skills/; MCP clients that support the Skills extension read it as skill://fbi-crime-guide/SKILL.md. It also ships in the npm package and Docker image.
fbi_search_agencies toolstate_abbr (required, two letters, case-insensitive) selects the state directory. Optional filters run over the whole state: name_contains (every word must appear in the agency name, any order, case-insensitive), county (equals any of the agency's counties), and agency_type (City, County, Other State Agency, Other, State Police, University or College, or Tribal).county ignores case, accents, spaces, periods, apostrophes, and hyphens (St. Louis matches ST LOUIS, Doña Ana matches DONA ANA). CDE lists county names without a County, Parish, or Borough suffix and keeps CITY on independent cities, so a name that matches no county in the state is retried without one trailing County, Parish, Borough, Census Area, Municipality, or City and Borough (Bexar County → BEXAR; Fairfax City stays FAIRFAX CITY).limit (default 50) and offset (default 0) page the matches, sorted by agency name then ORI. A limit above 200 returns 200 agencies with a notice naming both values; with FBI_CLAMP_LIMITS=false the schema advertises a maximum of 200 and rejects a larger value.state_abbr, total (matches before paging), offset, next_offset (absent on the last page), and agencies[] with ori, agency_name, agency_type, counties, is_nibrs, and nibrs_start_date when CDE lists one.AS, MP, or an unrecognized code) returns zero agencies with a notice; an offset past the end returns zero agencies with a notice naming the total.fbi_get_crime_estimates toolscope: national (no identifiers), state (only state_abbr, two letters), or agency (only ori, nine letters/digits; find it with fbi_search_agencies). Case is normalized to uppercase.offense: violent-crime, property-crime, robbery, burglary, larceny, motor-vehicle-theft, arson, aggravated-assault, rape, or homicide. Date range runs from_year/from_month through to_year/to_month (1985 through the current year; months default to January and December), and the start must not be later than the end. A year after the current UTC year fails with year_out_of_range; current-year months past the latest data return null values.entity_name, rates per 100,000 participating population, actual/clearance counts, and nullable population, participated_population, and population_coverage_percent for each offense month, plus data_last_updated and max_data_date when the provider supplies them.include_comparisons (default false; state or agency scope only) adds comparisons: one entry per comparison entity in CDE's order (an agency's state, then the United States; a state's United States), each { entity_name, months[] } with year, month, rate_per_100k, clearance_rate_per_100k, population, participated_population, and population_coverage_percent for exactly the scoped months. CDE sends no counts for comparison entities, and the list is empty when CDE sends none.scope_param_missing, scope_param_incompatible (also include_comparisons: true on national scope), year_out_of_range, invalid_date_range, no_data (also returned for a well-formed identifier the provider doesn't know).from/to echo it and total_months counts its months.fbi_get_hate_crimes toolscope, state_abbr, ori, and the from_year/from_month/to_year/to_month window follow the fbi_get_crime_estimates contract, with years from 1991 through the current year; counts are summed over the window.bias: all (default) or one of 34 CDE bias codes (11–85, listed on the field). With a code, incidents count that motivation plus multiple-bias incidents that include it.incident_section (bias, bias_category) and bias_section (offense_type, location_type, offender_race, offender_ethnicity, judicial_district) as category-to-count maps with every category CDE sends, zeros and nulls kept. The bias_section dimensions are counted on different bases and do not sum to one total or to the incident count. Also bias_label and data_last_updated when supplied.include_monthly (default false) adds monthly: one row per month of the window for the scoped entity, from CDE's monthly view (one more request, run in parallel). Each row has year, month, incident_count, offense_count, incident_rate_per_100k, offense_rate_per_100k, population, participated_population, and population_coverage_percent. CDE's -1 rate becomes null, and a count in a month whose participated_population is null is not a reported zero. The window returns whole.notice, since CDE returns zeros both for no reports and for an unrecognized state or ORI. With include_monthly the notice names the cause: an unrecognized state or ORI returns an empty monthly, while a recognized one returns its months, and when none of those months has a participated_population the notice says the zeros are not reported counts.scope_param_missing, scope_param_incompatible, year_out_of_range, invalid_date_range.fbi_get_arrests toolfbi_get_hate_crimes, with years from 1985 through the current year.offense: all (default) or one of 47 CDE numeric offense codes (for example 30 Robbery, 11 Murder and Nonnegligent Homicide, 320 Suspicion; listed on the field). Word slugs such as robbery are rejected. Code 23 (Rape - Not Specified) is excluded because CDE returns only zeros for it.140 and 150 are their category's "(Unspecified)" row, and 50 is the whole Aggravated Assault category. For a category total use offense: all and read offense_category. Multi-code categories: Homicide 11–12, Human Trafficking 101–102, Prostitution 140–143, Drug/Narcotic 150–160, Gambling 170–173, Vagrancy/Loitering 300 and 330.offense_name, offense_category, offense_breakdown, arrestee_sex, arrestee_race, male_arrests_by_age, and female_arrests_by_age as category-to-count maps, plus offense_label, `data_la