Adjust MCP
MCP 조정
Adjust API와 연동되는 간단한 MCP 서버로, Cursor나 Claude Desktop 등 모든 MCP 클라이언트에서 Adjust 데이터와 통신할 수 있습니다. 보고서, 지표 및 성과 데이터를 쿼리합니다. "2월 1일 캠페인 설치 수는 얼마입니까?"와 같은 온디맨드 조회에 적합합니다.
시간이 지남에 따라 Adjust API에 대한 내용을 더 추가할 예정입니다. 필요한 도구가 있는지 알려주시거나 PR을 열어주세요.
설치
Adjust 계정 설정에서 Adjust API 키를 받으세요.
Smithery를 통해 설치
Smithery 를 통해 Claude Desktop용 mcp-adjust를 자동으로 설치하려면:
지엑스피1
커서에 mcp-adjust를 설치하려면 설정 -> 커서 설정 -> 기능 -> MCP 서버 -> + 추가로 이동하세요.
유형 선택: 명령을 선택하고 Adjust의 API 키를 사용하여 아래를 붙여넣습니다.
npx -y @smithery/cli@latest run @bitscorp/mcp-adjust --config "{\"apiKey\":\"YOUR_ADJUST_API_KEY\"}"로컬에서 복제하고 실행
이 저장소를 복제합니다. npm run build 실행합니다. 이 명령을 Cursor(또는 다른 MCP 클라이언트) node /ABSOLUTE/PATH/TO/mcp-adjust/build/mcp-adjust.js YOUR_ADJUST_API_KEY 에 붙여넣습니다.
Related MCP server: meta-ads-mcp
예시
지난 7일 동안의 수익 보고서 조정을 사용하세요
Available Tools
2 toolsadjust-reportingD
Adjust reporting
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date for the report in YYYY-MM-DD format | 2026-01-03 |
| metrics | No | Comma-separated list of metrics to include | installs,sessions,revenue |
| dimensions | No | Comma-separated values to group by (e.g., day,country,network). Options include: hour, day, week, month, year, quarter, os_name, device_type, app, app_token, store_id, store_type, currency, currency_code, network, campaign, campaign_network, campaign_id_network, adgroup, adgroup_network, adgroup_id_network, creative, country, country_code, region, partner_name, partner_id, channel, platform | |
| format_dates | No | If false, date dimensions are returned in ISO format | |
| date_period | No | Date period (e.g., this_month, yesterday, 2023-01-01:2023-01-31, -10d:-3d) | |
| cohort_maturity | No | Display values for immature or only mature cohorts | |
| utc_offset | No | Timezone used in the report (e.g., +01:00) | |
| attribution_type | No | Type of engagement the attribution awards | click |
| attribution_source | No | Whether in-app activity is assigned to install source or divided | dynamic |
| reattributed | No | Filter for reattributed users | all |
| ad_spend_mode | No | Determines the ad spend source applied in calculations | |
| sort | No | Comma-separated list of metrics/dimensions to sort by (use - for descending) | |
| currency | No | Currency used for conversion of money related metrics | USD |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but fails completely. It doesn't indicate whether this is a read or write operation, what permissions might be required, whether it makes API calls, what format the output takes, or any other behavioral characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
While technically concise with just two words, this represents under-specification rather than effective brevity. The description fails to convey necessary information and doesn't follow the principle of front-loading critical details about the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex reporting tool with 13 parameters and no output schema, the description is completely inadequate. It provides no context about what kind of reporting system this interfaces with, what data it returns, or how it differs from the sibling tool. The lack of annotations exacerbates this incompleteness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% description coverage, so all 13 parameters are well-documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema, which meets the baseline expectation when schema coverage is complete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Adjust reporting' is a tautology that merely restates the tool name without providing any meaningful information about what the tool actually does. It doesn't specify what resource is being adjusted, what type of reporting is involved, or what action is performed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides absolutely no guidance about when to use this tool versus the sibling tool 'adjust-standard-report'. There's no indication of the appropriate context, prerequisites, or differences between these reporting tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
adjust-standard-reportC
Get a standard Adjust report with common metrics
| Name | Required | Description | Default |
|---|---|---|---|
| app_tokens | No | Comma-separated list of app tokens to include | |
| date_range | No | Date range (e.g., 2023-01-01:2023-01-31, yesterday, last_7_days, this_month) | last_7_days |
| report_type | No | Type of standard report to generate | performance |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Get' which implies a read operation, but doesn't specify permissions, rate limits, data format, or any side effects. This is a significant gap for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and appropriately sized, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't address behavioral aspects like authentication needs, error handling, or return format, which are crucial for a reporting tool. The high schema coverage doesn't compensate for these gaps in context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema fully documents all three parameters. The description adds no additional semantic context beyond what's in the schema, such as explaining interactions between parameters or usage examples, meeting the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('a standard Adjust report with common metrics'), making the purpose understandable. However, it doesn't explicitly differentiate from the sibling tool 'adjust-reporting', which appears to be a similar reporting tool, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as the sibling 'adjust-reporting'. There's no mention of prerequisites, constraints, or specific contexts for usage, leaving the agent with minimal direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- Changed
adjust-reporting1 field changed- changed
Input schema / properties / date / defaultPrevious value: -"2025-08-15"New value: +"2026-01-03"
2 tool updates
- First observed
adjust-reporting - First observed
adjust-standard-report
TDQS
Scored across 2 tools
The two tools have overlapping purposes related to Adjust reporting, which creates some ambiguity. 'adjust-reporting' is vague and could encompass standard reports, while 'adjust-standard-report' is more specific but may be a subset of the first tool. Descriptions help differentiate them, but the boundaries are not entirely clear.
Tool names follow a consistent pattern with 'adjust-' prefix and snake_case style, making them predictable and readable. There is a minor deviation in that one tool uses a hyphenated compound word ('reporting') while the other uses an underscore ('standard_report'), but overall the naming is mostly consistent.
With only 2 tools, the server feels too thin for a reporting domain, as it lacks basic operations like filtering, customization, or data export. This minimal set is insufficient for comprehensive reporting workflows, making it borderline inappropriate for the apparent scope.
The tool surface has significant gaps for a reporting server. It lacks essential operations such as creating custom reports, updating report parameters, deleting reports, or accessing detailed analytics beyond standard metrics. This incompleteness will likely cause agent failures in handling varied reporting tasks.
Maintenance
Related MCP Connectors
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Clamp Analytics MCP server: traffic, revenue, funnels, cohorts, errors, and search, for AI agents.
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA comprehensive MCP server for managing and analyzing Meta Ads (Facebook/Instagram) with over 80 natural-language tools for AI agents like Claude Desktop.-
- AlicenseAqualityDmaintenanceMCP server to manage Meta Ads (Facebook/Instagram) campaigns, ad sets, insights, and audiences from Claude Code using natural language.94 npmMIT
- AlicenseAqualityDmaintenanceMCP Server for the Meta Marketing API. Gives Claude Desktop direct access to your ad account data — campaign performance, creative analysis, audience breakdowns, and budget pacing.10206 npm1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for Google Ads campaign reporting and management via Claude, enabling GAQL queries, performance metrics, and campaign modifications.6 npmMIT