Model Context Protocol server for Rollbar
Nothing to run from here
DataFinder is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
19
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
DataFinder analytics with 52 tools, metric dictionaries, persistent jobs and confirmed changes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'DATAFINDER_AK=${DATAFINDER_AK}' --env 'DATAFINDER_SK=${DATAFINDER_SK}' --env 'DATAFINDER_PROJECT_ID=${DATAFINDER_PROJECT_ID}' --env 'DATAFINDER_APP_ID=${DATAFINDER_APP_ID}' --env 'DATAFINDER_SUBJECT_ID=${DATAFINDER_SUBJECT_ID}' --transport stdio datafinder-mcp '--' npx -y @cyuanxv/datafinder-mcp
# 2 — ask your agent for something these tools do
# mapping_import, business_contracts, analysis_workbench and 49 more
It needs DATAFINDER_AK, DATAFINDER_SK, DATAFINDER_PROJECT_ID, DATAFINDER_APP_ID, DATAFINDER_SUBJECT_ID: this reads them from your environment, so export them first.
DataFinder costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CYAll 4 servers
cyuanxv4 servers
3 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts DataFinder as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads DATAFINDER_AK (Your DataFinder access key), DATAFINDER_SK (Your DataFinder secret key), DATAFINDER_PROJECT_ID (Your DataFinder project ID), DATAFINDER_APP_ID (Your DataFinder app ID), DATAFINDER_SUBJECT_ID (Your configured analysis subject ID) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx DATAFINDER_AK …, setx DATAFINDER_SK …, setx DATAFINDER_PROJECT_ID …, setx DATAFINDER_APP_ID …, setx DATAFINDER_SUBJECT_ID … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'DATAFINDER_AK=${DATAFINDER_AK}' --env 'DATAFINDER_SK=${DATAFINDER_SK}' --env 'DATAFINDER_PROJECT_ID=${DATAFINDER_PROJECT_ID}' --env 'DATAFINDER_APP_ID=${DATAFINDER_APP_ID}' --env 'DATAFINDER_SUBJECT_ID=${DATAFINDER_SUBJECT_ID}' --transport stdio datafinder-mcp '--' npx -y @cyuanxv/datafinder-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs settings only you can give it: DATAFINDER_AK — Your DataFinder access key; DATAFINDER_SK — Your DataFinder secret key; DATAFINDER_PROJECT_ID — Your DataFinder project ID; DATAFINDER_APP_ID — Your DataFinder app ID; DATAFINDER_SUBJECT_ID — Your configured analysis subject ID. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
52 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
结构化候选映射最多5项；preview给出差异、固定模板/计划影响及hash；apply需confirmed和hash，仅保存草稿，逐项返回结果，不自动发布、不删除未出现项。来源需明确文档摘要和单元格，非自动Excel解析。
No parameter schema on file.
保存、回读、检查有版本的业务口径；未知项明确阻止结论。assess_experiment需固定实验版本和人工二元聚合，保留样本失衡检查，不宣告胜出。收入只保存定义，不计算净收入或首复购。
No parameter schema on file.
diagnose枚举最多3维组合、过滤小样本并排序线索，不合计重叠UV；bundle最多3项同日期同全局筛选分析，不计算缺成本ROI；capture确认后执行保存聚合证据，compare手工控制台单元格与固定查询指纹对照，仅证明所选数值匹配不证明语义。capture_query支持advanced/distribution；export需固定key和revision返回HTML证据报告。bundle/diagnose可带key、expected_revision和confirmed保存组合结果，保留历史。
No parameter schema on file.
固定模板和映射版本，保存默认预览；升级先preview_upgrade再confirmed及hash。tick复用云端队列，昨天完整日期，不自动迁移或删除。模板新版须显式升级计划；执行前校验映射。
No parameter schema on file.
save默认预览，confirmed保存草稿；validate读取实时元数据给出validation_hash；publish需confirmed、expected_revision和hash，追加发布版本。planned不能发布。read/history/list保留历史；run按指定revision或日期选择最新适用发布版本，query不传events/filters/revenue_property，extra_filters只追加AND筛选。query也支持user_frequency/user_cumulative_measure/numeric_event_distributio…
No parameter schema on file.
仅配置的应用的普通事件、事件属性、用户属性定义；read读取，preview保存差异，apply用change_id及confirmation明确确认后提交，change回读变更。用户属性可创建；不支持删除或已有属性类型转换。
No parameter schema on file.
周期/显式群体对比、事件次数贡献拆解、group_diagnosis多维群体UV变化排序（一个事件、baseline及group_by，识别重叠，不计算可加总UV贡献）、漏斗损失、留存队列、日级时间规律和关联、hourly_pattern小时规律（最多7个完整自然日、3个事件，上海时区次数，不相加小时UV）；revenue_quality查询一个支付事件的数值revenue_property合计、人数和跨期因素拆解，订单去重/币种/退款未核验，不等于净收入。输入明确period、events和filters；周期需等长不重叠baseline；贡献需group_by且仅分解事件次数。未知不补零…
No parameter schema on file.
save/revise默认预览，confirmed后保存新版本；read回读；run需expected_revision。可保存mapped_definition绑定已发布映射key/revision/query/extra_filters，run实时校验元数据；追问changes继承固定映射版本，不能改映射事件或金额字段。未指定字段继承，数组整体替换；先展示差异。不删除历史、不修改火山对象。
No parameter schema on file.
对调用者明确提供的两组分配/二元转化人数计算比例、样本失衡和固定终点近似检验。来源未独立核验；小样本、未成熟、未确认随机化或持续偷看时不输出显著性。不是DataTester原生接口。
No parameter schema on file.
本人规则模板搜索和分页导出；preview/apply按完整目标配置逐项版本校验，确认后提交，可部分失败；trend要求规则版本，分页读取原始数值与状态；audit读取配置版本前后差异；result按任务ID和子任务读取可绘图的已保存聚合结果。扩展trend_export/audit_export分页CSV、compare同模板版本同日期比较、retry_preview最新版本差异、diagnostics重试历史、integrity任务结果校验。不删除数据，不修改火山看板。
No parameter schema on file.
本人规则和模板管理：catalog搜索元数据，values按事件日期读取属性值，validate检查草稿，trial最多3天只读试跑不保存观测；action=workflow的payload={definition,changes?,execute?,preview_hash?}；definition:{dictionary:{key,revision}}可直接使用已绑定表列的SQL指标，不传日期；也可用saved_sql:{report_id,source_version,count,selection:{table_index,columns}}。SQL追问changes:{saved_…
No parameter schema on file.
读取本人调度触发、任务进度、耗时、错误码、租约中断和每日计划下次名义时间；不会执行任务。服务收到tick不证明平台自动触发，需对照平台运行历史；view=jobs/attempts/dispatches支持cursor分页、status及带时区的from/to时间筛选，overview包含全量任务状态及剩余子任务统计、最近连续调度失败、90分钟停滞提示和需要升级的计划；不把手动调用当自动触发。
No parameter schema on file.
提交虚拟对象依赖扫描到云端队列，每次调度扫一页并持久化检查点；自动续扫、跨页去重、目录或元数据变化拒绝继续。按job_id回读进度；coverage始终partial，不包含不可见报表。提交不代表执行完成。
No parameter schema on file.
检查云端配置状态；配置存在不代表真实查询已验收。
No parameter schema on file.
实时搜索项目内账号可见的看板和报表；事件与属性元数据仅限配置的应用，报表按批准的项目范围读取。
No parameter schema on file.
读取项目内任意有权限看板的页面、布局和报表关联。可传id；dashboard_id保留兼容。
No parameter schema on file.
解释已保存配置中的事件、分子分母、去重、留存起始/回访事件、筛选和依赖。业务名称不代替真实口径。
No parameter schema on file.
读取项目内账号有权限的任意报表，无固定报表名单。可同时提供 start_date/end_date（YYYY-MM-DD，北京时间完整自然日，最长31天），临时覆盖日期并保留原生公式；不修改保存配置。省略日期则读取原配置；临时 filters/group_by 需明确日期，走原生分析，filters 与原筛选取交集、group_by 替换原分组。检查 validation/status…
No parameter schema on file.
受控重放已保存的事件/留存 DSL，仅替换日期。日期是北京时间完整自然日，最长 31 天；不接受任意 DSL、SQL、字段或应用。契约未验收时拒绝执行。
No parameter schema on file.
自由事件可传formulas，A–E绑定events顺序，支持四则运算括号；插件按同日期同分组派生计算，缺失/除零未知，人数比值非漏斗；需第1指标页包含全部事件。公式不修改火山原生指标。不依赖已有报表创建事件/留存分析：事件传events，留存传initial_event/return_event；或仅传report_id沿用原口径。筛选用真实属性名/类型；filters数组外层为AND，可包含{logic:and或or,conditions:[条件]}分组，最多两层组；组内条件不能空。当前项目用户属性通常为user_profile。自由事件支持granularity=hour（最多7天）、…
No parameter schema on file.
按事件和日期读取属性值组合，支持上游分页。properties使用真实属性名和类型；不提供标识符/消息内容明细。该工具列出值，不返回频次；频次用run_analysis分组查询。
No parameter schema on file.
查询指定事件次数与区间人数，对比前几周相同星期区间。最多7天、5个事件；返回异常线索而非故障结论，不自动通知。
No parameter schema on file.
按事件次数统计属性null、空字符串，以及明确字符串白名单以外的非空值。可用numeric_bounds检查原始数值属性的含边界范围，required_when限定必填条件与比例分母；白名单与数值规则不可混用。不读取用户明细。
No parameter schema on file.
2至8步去重人数有序漏斗；window={value,unit:minute/hour/day}指定滚动窗口，最长7天；兼容window_days，两者不能同时传。分钟/小时/天滚动窗口已完成控制台对照；不支持当天截止。允许后续步骤延伸到结束日期之后，未成熟窗口拒绝执行。仅聚合、不保存报表。
No parameter schema on file.
读取用户属性名、类型、展示名与说明，不读取用户值。限配置的应用，返回目录快照的本地分页及完整性边界。
No parameter schema on file.
在相同日期和相同显式渠道/平台等controls下，对比新旧版本的事件次数、区间人数、人均次数，可同时传funnel_steps与quality。版本用原始common_param属性。只做描述性对照，不推断因果；没有controls时未控制流量混杂。
No parameter schema on file.
user_cumulative_measure按每用户累计数值属性分桶，需要event、event_param property和非负递增boundaries；不转换单位、不去重订单。user_frequency按每个日或区间内累计事件次数统计用户分布，需要event和正整数boundaries、不传property，分桶与独立UV校验，零次用户不包含。numeric_event_distribution按单次事件属性分桶统计事件次数；必须指定递增边界，空值单列并校验守恒。成分分析按用户属性返回人数，上游日期与分母未独立验证时为incomplete，不能据此下结论。
No parameter schema on file.
生命周期、LTV、首触/末触/线性归因、事件次数TopK和路径分析。LTV events顺序为收入事件、队列事件，必须提供数值收入属性；生命周期仅1天窗口。归因使用控制台核验的六列指标：触发次数、有效触发次数/率、目标次数、贡献度和相关性；window为回溯天数，不代表当天。路径window为会话间隔分钟，输出已核验列含义的流量边，不能解释为去重人数；上游日期未回读时整体仍为incomplete。失败不得解释为空数据。
No parameter schema on file.
只读取配置的应用标签目录、类型和计算状态；不读取成员或标签值。上游失败不解释为没有标签。
No parameter schema on file.
配置的应用规则分群：读取完整定义，预览创建/替换规则/刷新。支持最近1至31天某事件至少N次及事件筛选；不上传或读取成员。必须展示预览并经用户确认才apply；写入未知不自动重试。
No parameter schema on file.
读取配置的应用分群名称、计算状态和最近人数，不读取成员。
No parameter schema on file.
查询配置的应用每日DAU和事件用量，不是计费金额或业务口径。
No parameter schema on file.
生成本人登录后可下载的CSV或Excel XML链接；源为持久巡检批次或云端任务，保留质量状态和配置，不补零、不重算；链接生成不证明下载成功。
No parameter schema on file.
本人每日巡检计划，指定上海小时和规则版本，检查前一完整自然日；更新需confirmed和expected_revision。tick由云端调度调用，幂等入队并处理一个任务。preview_backfill检查最多31日，backfill需preview_hash、dates和confirmed，默认mode=missed仅补当时启用且到期的漏跑日期；mode=specified按当前保存口径明确补查选定日期，不声称历史漏跑；绑定规则变化则拒绝。preview_upgrade需keys（最多10个），返回规则新旧差异与各计划preview_hash；upgrade需upgrades:[{key…
No parameter schema on file.
提交最多20个模板、巡检或后台依赖扫描子任务，用request_key去重。list支持cursor/status/from/to；read读取概要；pause/resume/cancel需confirmed，运行中暂停在当前查询结束后生效，取消仅限等待或暂停；read_merged返回至所选恢复任务的合并状态及来源，完整合并用merged_job导出；分块结果用read_result指定task_index与result_page按序读取并校验。retry需confirmed=true与新request_key，仅恢复失败/未执行部分并关联原任务；模板/规则及依赖指纹变化时拒绝继续。单个结…
No parameter schema on file.
保存或更新本人云端模板需confirmed与expected_revision；日期在执行时显式提供，报表模板绑定来源口径版本，漂移拒绝执行。结果完整性仍以output为准。
No parameter schema on file.
读取或更新某次巡检观测的人工处理状态（unread未查看、acknowledged已查看、investigating处理中、resolved已处理）、备注及关联巡检任务。更新需expected_revision、confirmed、note、job_id（无关联传null）；已处理需说明。人工已处理不代表数据恢复；保留版本历史，不发送消息。
No parameter schema on file.
预览后用preview_hash及confirmed确认手动归档或恢复；只影响默认任务列表，不删除结果、不改变恢复链或调度去重。未结束任务不能归档。批量可能部分冲突，按results逐项回读。
No parameter schema on file.
读取本人JSON与结果字段的UTF-8字节用量，预览历史任务归档候选及恢复链保留原因；不归档、不删除、不承诺释放空间。
No parameter schema on file.
读取巡检产生的业务异常线索、执行失败和恢复记录；未知/无数据不算恢复，同版本连续异常去重；transitions先对全历史推导再筛选分页，恢复记录关联上一条非未知状态变化；observations读取逐次检查；未知及旧日期补跑不恢复新日期异常，不发送外部通知。
No parameter schema on file.
分析前优先 list 按名称或别名检索，再 read 核对使用建议、默认来源、来源变化及成熟窗口。无匹配明确说明未使用正式指标。source/catalog 读取来源；preview_import 仅预览。save 不传 confirmed 生成预览，展示完整内容经用户确认后带 preview_hash 保存；save_batch…
No parameter schema on file.
读取报表配置和版本，先解释口径，再请用户确认业务含义；保存时绑定此版本。
No parameter schema on file.
保存本人云端记录，不修改DataFinder。必须展示完整内容并获得用户确认后传confirmed=true。新建expected_revision=0；更新需最新版本，保存为不可变新版本。指标需来源版本；规则保存不执行、不发通知。
No parameter schema on file.
读取当前用户记录；指定key和revision可读取历史。指标单条读取会检查来源配置漂移，列表不检查；字典文字是用户业务约定，不是上游事实。
No parameter schema on file.
传1至5条规则key及当前revision、日期。逐条执行，失败不终止其余；预算不足标记未执行，不能视为正常。保存聚合结果供后续读取，无通知。
No parameter schema on file.
读取本人云端保存的聚合检查结果，历史结果不代表当前数据。
No parameter schema on file.
每页3个可见看板，可用max_pages一次合并最多10页并去重报表。后续页带catalog_version；max_depth控制结构化传递链深度。SQL词法候选排除注释和普通字符串，但不证明语义依赖。未关联或不可见报表仍未覆盖，coverage始终partial，无匹配不代表无影响。
No parameter schema on file.
读取完整保存规则、SQL表达式、关联与版本。元数据限定配置的应用；查询数据使用run_analysis或inspect_property_values并指定virtual类型。
No parameter schema on file.
预览创建或修改虚拟事件/属性并保存15分钟有效的云端草稿；不会修改DataFinder。修改前应调用scan_virtual_dependencies并展示覆盖范围。必须向用户展示差异和影响，获得本次确认后才能apply。修改虚拟事件不支持description描述字段，传入即拒绝，其他字段也不会提交；创建及虚拟属性不受此限制。虚拟事件规则仅支持原始事件OR组合；属性使用受限标量SQL表达式；不支持删除。
No parameter schema on file.
仅在用户确认本次预览后调用；传preview返回的change_id和confirmation。仅提交一次，超时状态unknown时先读取对象核对，不自动重试。
No parameter schema on file.
读取当前用户的云端预览、执行状态与回读结果；unknown/applying不是成功，不得自动重发。
No parameter schema on file.
仅支持项目可见看板关联的已保存SQL报表。先action=read读取定义和版本，再经用户查询请求action=execute并传expected_version。可用selection按明确table_index和columns选择返回列；先action=preview获取preview_hash，再execute原样回传；行数、列名或来源改变须重新预览。支持已保存的完整事件日期参数，动态日期须固定预览；不接受临时参数覆盖。按保存配置读取原生结果，不接收任意SQL，不改写日期，不保证绕过缓存。
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install DataFinder or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 0.2.5 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest94103a5a11293316e6c724637fe0447512297054d59e614235e33b6c11324de2
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest94103a5a11293316
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.5. Pin a release below and the command asks for exactly that one.
0.2.5
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish DataFinder can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.