一个无依赖的 Model Context Protocol (MCP) 服务器，用于 Tempo.co 的公开报道。它支持获取文章、Tempo 搜索、文章级研究简报，以及跨持续发展故事的比较。
tempo_search — 查找查询的公开 Tempo 链接。
tempo_article — 返回规范化的文章元数据、干净文本，以及相关的视频/嵌入元数据（如果存在）。
tempo_insights — 生成包含主张、实体、日期、量化信号、不确定性和相关视频上下文的抽取式简报。
tempo_compare — 对比两到五篇文章，找出重复的实体、主张和时间线信号。
tempo_auth_status — 报告是否配置了可选的订阅者身份验证，而不暴露机密。
分析工具不独立验证报道。它们明确将输出标记为从获取来源中提取的信号。
Related MCP server: Real Time News Data MCP Server
如果 Tempo 文章包含相关视频，服务器会尝试从公开文章 HTML 中可用的内容提取可用上下文：
JSON-LD VideoObject、Clip 或 MediaObject 元数据。
OpenGraph 视频 URL。
嵌入的视频 iframe，如 YouTube、Vimeo 或其他播放器嵌入。
原生 HTML 视频源和字幕轨道链接。
转录文本（当页面在结构化元数据中公开时）。
tempo_insights 将该视频元数据或转录文本合并到 related_video_context 下的简报中。它不会自行下载视频、绕过播放器或转录音频；如果 Tempo 仅嵌入视频而没有字幕、转录、标题或描述，则洞察将仅限于嵌入元数据。
添加以下服务器定义，如果您的检出位于其他位置，请替换绝对路径：
{
"mcpServers": {
"tempo-insights": {
"command": "node",
"args": ["/Users/yudistryanizharkamil/Documents/ChatGPT/Personal/src/index.js"]
}
}
}无需 npm install 步骤。使用 npm start 手动运行。
Tempo.co 似乎没有为第三方文章访问公开 OAuth 流程。Tempo 使用 REMP：登录用户令牌位于 n_token cookie 中，也作为 Authorization: Bearer <n_token> 发送。Hotjar _hjSession_* 或 _ga 等分析 cookie 不是登录凭据。
对于已订阅的账户，MCP 支持通过环境变量进行身份验证获取：
TEMPO_COOKIE — 一个 Cookie 头，或一个裸 n_token 值。跟踪 cookie 会被剥离；裸令牌会规范化为 n_token=...。
TEMPO_COOKIE_FILE — 包含该 cookie 的文本文件的路径。每次请求都会重新读取该文件。
TEMPO_AUTHORIZATION — 可选的覆盖项。如果省略，MCP 会从 cookie 派生 Bearer <n_token>。
这不会绕过 Tempo Plus。它只允许 MCP 获取您的账户已被允许访问的内容。MCP 永远不会打印 cookie 值。
在 Chrome 中登录 Tempo，然后运行：
npm run cookie:export该辅助程序从您的本地配置文件中读取 Chrome 的 Tempo cookie，仅保留 n_token、we_userid、status_user、remp_session_id、remp_session_referer 和 browser_id，并将它们写入 ~/.cursor/tempo.cookie。除非您运行它，否则它不会抓取 cookie。
然后将 Cursor 指向该文件并重新加载 MCP：
{
"mcpServers": {
"tempo-insights": {
"command": "node",
"args": ["/Users/yudistryanizharkamil/Documents/ChatGPT/Personal/src/index.js"],
"env": {
"TEMPO_COOKIE_FILE": "/Users/yudistryanizharkamil/.cursor/tempo.cookie"
}
}
}
}使用 tempo_auth_status 确认 n_token_present 和 subscribed_cookie_present。如果 Chrome 使用 v20 应用绑定加密，请从 DevTools 中复制您已能阅读的 Tempo Plus 文章上的 Cookie 头，将其保存到同一文件，然后重新运行。
仅接受主机名为 tempo.co 或 Tempo 子域的 HTTPS 链接。响应在内存中缓存五分钟，以活动身份验证头的短哈希为键，因此匿名、静态 cookie 和 cookie 文件获取不会冲突。服务器使用类似浏览器的 User-Agent，源获取在 15 秒后超时，并将提取的文章文本限制在 35,000 个字符。
Tempo 的页面标记可能会变化。文章提取器首先使用 JSON-LD 获取元数据，使用 __NEXT_DATA__ 和文章正文回退获取文本，并使用媒体回退获取相关视频上下文；如果页面发生变化，请更新 src/index.js 中的 extractBody 或 relatedMedia。
Fetch one public Tempo.co article and return clean text plus normalized metadata. Use this before requesting a deep insight for a particular URL.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | A public www.tempo.co (or Tempo subdomain) article URL. | |
| include_body | No | ||
| include_media | No | Include related video/embed metadata found on the article page. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It states the tool fetches and returns data, implying a read-only operation, but does not explicitly state whether it is safe, requires authentication (given the presence of tempo_auth_status), or has any side effects or limitations (e.g., only public articles). This lack of behavioral disclosure is a gap.
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?
Two sentences with no filler. The first sentence states the function, and the second gives a clear usage directive. Information is front-loaded and every word is purposeful.
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?
The tool is relatively simple (one required param) and the description covers the main purpose and a usage hint. However, it lacks an output schema and does not mention behavioral constraints like authentication (despite the existence of tempo_auth_status), error handling, or any caveats about availability of public articles. An agent might not know if it needs to call tempo_auth_status first or what specific metadata fields to expect. So it is adequate but not complete.
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 input schema already describes the url and include_media parameters, providing 67% coverage. The description adds a general sense of the output ('clean text plus normalized metadata') but does not elaborate on the parameters beyond what the schema provides. The include_body parameter lacks a schema description, and the tool description doesn't compensate for that either. Minimal added value over the schema.
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 states a specific verb ('Fetch'), a specific resource ('one public Tempo.co article'), and the output ('clean text plus normalized metadata'). It also hints at a relationship with 'deep insight' (likely tempo_insights), which helps disambiguate from siblings.
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 explicitly says 'Use this before requesting a deep insight for a particular URL', which tells the agent when to use this tool relative to tempo_insights. It does not list other alternatives like tempo_search or tempo_compare, but it provides clear usage context for the primary workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Report whether optional subscriber authentication headers are configured for Tempo fetches. Does not expose secrets.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose that it does not expose secrets, which is a useful behavioral safety note. However, it does not mention potential side effects (though there likely are none), error behavior, or whether it makes any network calls. The security disclaimer adds value, but for a tool with zero annotations, more explicit behavioral context would be expected.
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?
Two short sentences, front-loaded with the core purpose ('Report whether optional subscriber authentication headers are configured') followed by a valuable safety qualifier ('Does not expose secrets'). Every word earns its place; no fluff.
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 tool has no parameters and no output schema, the description provides the essential information an agent needs: what the tool reports and a critical security property. It is complete for a status-check tool, with no obvious gaps.
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 tool has zero parameters, so per the rubric the baseline is 4. The description does not need to add parameter meaning since there are none. It correctly focuses on the tool's purpose without unnecessary parameter discussion.
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 uses a specific verb 'Report' and a precise object 'whether optional subscriber authentication headers are configured for Tempo fetches.' It clearly states what the tool does and distinguishes itself from siblings like tempo_search and tempo_article, which perform different operations. Even without reading the schema, an agent can tell this is a status check.
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 gives no explicit guidance on when to use this tool versus the sibling tools. It implies it is a read-only status check, but does not state conditions for invocation, such as 'call this before attempting authenticated fetches' or 'use when you need to verify configuration.' Lacks any when-to-use or when-not-to-use context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compare 2–5 Tempo.co articles. Highlights shared entities, repeated facts, differing framing, chronology, and reporting gaps. Useful for tracking a developing story.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | ||
| focus | No | Optional comparison lens. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It describes what the comparison highlights, which is useful, but does not disclose any constraints like authentication requirements, potential latency, or failure modes. The tool appears to be read-only, but this is not explicitly stated. It is not misleading but lacks depth on behavioral traits.
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?
Two concise sentences with no fluff. The core purpose is front-loaded, followed by a use-case example. Every word earns its place.
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 tool has 2 parameters, no output schema, and no annotations, the description covers purpose, range, and use case, but omits details about the focus parameter and any prerequisites (e.g., whether URLs must be publicly accessible). An agent could likely call the tool correctly but might not understand the full scope of the focus lens or output format.
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?
Schema coverage is 50%; the focus parameter's description ('Optional comparison lens') is vague. The tool description clarifies that the urls parameter should contain article URLs, but it does not elaborate on the focus parameter or its possible values. It adds some meaning to urls but falls short of compensating for the gap on focus.
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 verb ('Compare'), the resource ('Tempo.co articles'), and the scope (2–5 articles). It also lists specific outputs (shared entities, repeated facts, framing, chronology, gaps) and is distinct from sibling tools that search, fetch single articles, or provide insights.
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 gives clear context with 'Useful for tracking a developing story' but does not explicitly contrast with alternatives like tempo_search or tempo_insights. It implies use when multiple articles exist for comparison, but lacks explicit exclusion criteria or mentions of alternative conditions. Slightly above baseline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Turn a Tempo.co article into a research brief: executive summary, key claims, named entities, timeline signals, numbers, uncertainties, and questions to investigate. It is extractive and explicitly separates reported facts from inferred themes.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| focus | No | Optional lens, e.g. 'policy implications', 'company risk', or 'election timeline'. | |
| include_source_text | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the extractive nature and that it separates facts from inferred themes, which is genuinely useful. However, it fails to mention anything about authentication requirements (the sibling tempo_auth_status hints auth is a real concern), output format, failure modes for non-Tempo URLs, or whether it caches results. For a tool that processes external URLs, these are material gaps.
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?
A single, information-dense sentence that front-loads the primary action and then enumerates the output artifacts. No wasted words, and the extractive/facts-vs-inference clause earns its place by adding behavioral nuance. It is concise without being terse.
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?
The description covers the tool's purpose and output structure well, but with no annotations and no output schema, an agent has to infer the return shape, error behavior (e.g., what happens for non-Tempo URLs or paywalled content), and whether auth is required. For a tool that ingests an external URL and produces a multi-part brief, these operational details matter. The facts-vs-inference separation is a nice touch but doesn't compensate for missing auth and error semantics.
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?
Schema coverage is only 33%. The description names the focus parameter's purpose indirectly through the research-brief concept, but it doesn't explain what 'focus' does mechanically (narrow the extraction? bias the output structure?) beyond the example lens. The url parameter is obvious from the description ('Tempo.co article'), and include_source_text is self-explanatory from its boolean type. The description adds marginal context but doesn't fully compensate for the coverage gap on 'focus'.
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?
States a specific verb ('Turn into a research brief'), a clear resource (Tempo.co article), and enumerates the output structure (executive summary, key claims, named entities, timeline signals, etc.). It also distinguishes itself by characterizing its approach as 'extractive' with an explicit facts-vs-inference separation, which is unique among the listed siblings.
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?
No guidance on when to use this tool versus tempo_article, tempo_compare, or tempo_search. An agent cannot tell from the description whether it should run tempo_insights or tempo_article for a single article, or whether tempo_compare handles multi-article comparison. Sibling names suggest the comparison tool exists, but the description never mentions alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Tempo.co reporting by a query. Returns article candidates with title, URL, date, description, and section when available.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Indonesian or English search phrase. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that results are 'candidates' with specific fields, but it does not mention potential side effects (e.g., read-only nature), authentication requirements (given sibling tempo_auth_status exists), or pagination/result limits beyond the schema. It provides some behavioral context but leaves gaps.
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 two sentences, clear, and front-loaded with the main purpose. It avoids redundancy and includes only relevant information about what is returned. No filler or excessive detail.
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 simple search tool, the description covers the query and return fields, but it lacks critical context such as authentication prerequisites (sibling tempo_auth_status implies auth may be needed) and any pagination or limit behavior. It does not mention sorting or how results are ordered, which an agent might need to know. Essential enough to score a 3, but not complete.
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 covers 'query' with a description, but 'limit' has no description and the tool description does not mention either parameter. The description adds no value beyond the schema for the query parameter and fails to compensate for the undocumented limit parameter. Since schema coverage is 50% (not low, but not high), the description should at least reference the limit behavior; it does not.
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 states a specific verb ('Search'), resource ('Tempo.co reporting'), and what it returns (article candidates with fields). It clearly distinguishes from siblings like tempo_article (likely retrieval of a specific article) and tempo_insights (likely analysis), so an agent can tell it apart without inspecting other tools.
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 implies usage when you have a query, but it does not explicitly mention when to use this tool versus alternatives. Sibling names suggest tempo_article is for specific article retrieval, but the description does not state 'use tempo_article when you have a direct URL' or similar exclusions. Guidance is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: search, fetch, generate insights, compare, and check auth status. No overlap or ambiguity exists between them, making tool selection straightforward for an agent.
All tools share the 'tempo_' prefix and use snake_case, but there's a mix of verb-led names (tempo_search, tempo_compare) and noun-led names (tempo_article, tempo_insights, tempo_auth_status). Minor inconsistency, but the pattern is still predictable and readable.
With exactly 5 tools, the set is well-scoped and each tool earns its place in the news analysis workflow. This falls comfortably within the ideal range for a specialized server.
The core workflow of searching, fetching, analyzing, and comparing articles is covered, plus a useful auth status check. Minor gaps like bulk fetching or topic discovery exist, but they are not critical to the server's purpose and can be worked around.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search, read, and automate TextMine documents, records, workflows, integrations, and agent tasks.
Search and analyze global news coverage and US TV transcripts via the GDELT Project APIs.
Summarize URLs, repurpose content, daily news digests, find competitors. Cost telemetry built in.
Real-time web search, reasoning, and research through Perplexity's API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yudistryan/tempo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
