Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@py-har-mcp Load the HAR file from /path/to/capture.har and list all URLs and methods"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
一个用于解析和分析 HAR（HTTP Archive）文件的 Model Context Protocol (MCP) Python 服务器。这个服务器允许 AI 助手检查 HAR 格式捕获的网络流量，并内置对敏感认证请求头的自动脱敏支持。
加载 HAR 文件：支持本地文件系统路径和 HTTP/HTTPS URL
列出全部 URL 与 HTTP 方法：查看 HAR 中访问过的请求组合
查询请求 ID：根据 URL 与 Method 获取对应请求 ID
获取完整请求详情：自动脱敏认证请求头，并尽量以纯文本输出响应内容
按域名统计请求：汇总域名级别的请求数、方法分布、状态码分布
按状态码统计请求：统计各 HTTP 状态码出现次数及关联请求 ID
全文搜索 HAR 内容：支持搜索请求头、响应头、请求体、响应体
兼容真实世界 HAR 文件：
time 和 timings 字段支持整数/浮点数并自动转为整数
response.content.text 支持普通文本或 base64 文本，并优先输出纯文本
允许 HAR 中存在标准规范之外的附加字段
支持浏览器开发者工具导出的标准 HAR 格式
Related MCP server: Android Proxy MCP
你可以通过标准 MCP 配置方式安装和运行这个 MCP 服务器。
将如下 JSON 配置加入你的 MCP 配置文件。
如果你使用 uv，可以直接通过 uvx 运行：
{
"mcpServers": {
"py-har-mcp": {
"command": "uvx",
"args": [
"py-har-mcp"
]
}
}
}也可以直接通过 python -m 启动服务器。
{
"mcpServers": {
"py-har-mcp": {
"command": "python",
"args": [
"-m",
"py_har_mcp"
],
"cwd": "D:\\Project\\py\\har-mcp\\py-har-mcp"
}
}
}如果你不想依赖 uvx，可以先在项目根目录安装源码：
pip install -e .安装后可直接把命令配置为 py-har-mcp：
{
"mcpServers": {
"py-har-mcp": {
"command": "py-har-mcp"
}
}
}py-har-mcp 以基于 stdio 的 MCP 服务器方式运行，通过标准输入/输出进行通信。
在 py-har-mcp 目录下执行：
python -m py_har_mcp或：
py-har-mcp如果你希望以 HTTP 方式运行：
python -m py_har_mcp --http --port 8000仓库已提供 GitHub Actions 工作流 py-har-mcp/.github/workflows/publish.yml，用于自动构建并发布新版本到 PyPI。
发布 GitHub Release 时自动触发
也可以在 GitHub Actions 页面手动触发
在 GitHub 仓库的 Settings > Secrets and variables > Actions 中新增 Secret：PYPI_API_TOKEN
Token 建议使用 PyPI 的项目级或账号级 API Token
创建一个新的 GitHub Release，工作流就会自动：
安装构建工具
构建 sdist 和 wheel
执行 twine check
上传到 PyPI
更新 py-har-mcp/pyproject.toml 中的版本号
提交代码并推送到 GitHub
创建对应版本的 Tag / Release
等待 GitHub Actions 自动发布到 PyPI
load_har加载 HAR 文件，并将其保存为默认分析数据集。
Parameters:
source (string, required): HAR 文件路径或 HTTP/HTTPS URL
Example:
{
"source": "D:\\captures\\demo.har"
}list_urls_methods列出 HAR 中所有访问过的 URL 与 HTTP 方法组合。
Parameters:
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用已通过 load_har 加载的默认 HAR
Returns: 带有 URL、Method 和关联请求 ID 的数组。
get_request_ids根据指定 URL 和 HTTP 方法获取请求 ID 列表。
Parameters:
url (string, required): 要匹配的完整请求 URL
method (string, required): 要匹配的 HTTP 方法，如 GET、POST
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用默认 HAR
Example:
{
"url": "https://api.example.com/users",
"method": "GET",
"source": "D:\\captures\\demo.har"
}get_request_details根据请求 ID 获取完整请求详情。认证相关请求头会被自动脱敏。
Parameters:
request_id (string, required): 要查询的请求 ID，例如 request_0
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用默认 HAR
Example:
{
"request_id": "request_0",
"source": "D:\\captures\\demo.har"
}Redacted Headers:
Authorization
X-API-Key
X-Auth-Token
Cookie
Set-Cookie
Proxy-Authorization
get_domain_stats按域名汇总请求统计信息，包括方法分布和状态码分布。
Parameters:
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用默认 HAR
Returns: 包含 domain、total_requests、methods、status_codes 的数组。
get_status_code_stats按 HTTP 状态码汇总请求统计信息。
Parameters:
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用默认 HAR
Returns: 包含 status_code、count、request_ids 的数组。
search_har在 HAR 中搜索请求头、响应头、请求体和响应体内容。
Parameters:
query (string, required): 搜索关键字或片段
search_headers (boolean, optional): 是否搜索请求头和响应头，默认 true
search_request_body (boolean, optional): 是否搜索请求体，默认 true
search_response_body (boolean, optional): 是否搜索响应体，默认 true
case_sensitive (boolean, optional): 是否区分大小写，默认 false
source (string, optional): 指定 HAR 文件路径或 URL；为空时使用默认 HAR
Returns: 包含 request_id、location、field、snippet、url、method、status_code 的匹配结果数组。
将如下配置加入 Claude Desktop 的 MCP 配置文件：
{
"mcpServers": {
"py-har-mcp": {
"command": "uvx",
"args": ["py-har-mcp"]
}
}
}如果你使用本地源码，也可以改为 python -m py_har_mcp 或 py-har-mcp。
MIT
按域名汇总请求统计信息，包括请求方法和状态码分布。
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | 可选 HAR 文件来源。为空时使用默认 HAR；传入时直接分析指定 HAR 文件。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of disclosure. It states the aggregation behavior and included metrics, but does not clarify whether results are counts, percentages, or raw lists, nor does it explicitly confirm read-only behavior or handle empty-data scenarios. The name 'get_' and statistical nature imply safety, but the description alone offers limited depth.
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, front-loaded sentence that directly states the verb and resource. It contains zero redundant text and fully conveys the core functionality in a compact form.
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's simplicity and the presence of an output schema, the description adequately covers the purpose and grouping scope. The only gap is the lack of explicit differentiation from sibling tools like get_status_code_stats, but the 'by domain' phrase provides sufficient context for an agent to select this tool.
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 description coverage is 100% because the only parameter, 'source', has a full description explaining its behavior. The tool description does not add parameter-specific meaning beyond the schema, but the baseline of 3 is appropriate given the high 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 a specific verb '汇总' (summarize/aggregate), the resource '请求统计信息' (request statistics), and the grouping key '按域名' (by domain), while specifying included dimensions (method and status code distribution). This distinguishes it from sibling tools like get_status_code_stats, which likely provides overall stats.
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 use case is implied: '按域名汇总' suggests using this tool when domain-level breakdowns are needed. However, there is no explicit guidance about when to use this tool versus alternatives like get_status_code_stats or list_urls_methods, and no mention of when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
根据请求 ID 获取完整请求详情，并自动脱敏认证相关请求头。
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | 可选 HAR 文件来源。为空时使用默认 HAR；传入时直接分析指定 HAR 文件。 | |
| request_id | Yes | 请求 ID，格式通常为 `request_0`、`request_1`。可由 `list_urls_methods` 或 `get_request_ids` 返回。 |
| Name | Required | Description |
|---|---|---|
No output 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 discloses a notable behavioral trait: automatic redaction of authentication-related headers. However, it does not explicitly state whether the operation is read-only or non-destructive, nor describe any side effects. The redaction disclosure is valuable but incomplete for a tool with no annotation support.
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, compact sentence that front-loads the primary action and adds the redaction behavior without redundancy. Every word contributes value.
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 is concise and mentions the key redaction behavior, and an output schema exists to define return structure. However, it does not explicitly place the tool in the flow of using sibling tools (e.g., 'Use get_request_ids first to obtain an ID'), which would enhance completeness for an agent deciding when to invoke it.
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 provides 100% coverage for both parameters, including descriptions for request_id and source. The description text adds no additional parameter-specific meaning beyond reaffirming that it retrieves details by ID. Baseline 3 is appropriate since the schema already documents the parameters thoroughly.
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 ('获取' - retrieve) and resource ('完整请求详情' - full request details), scoped by request ID. It also adds a distinct feature (auto-redaction of auth headers) that differentiates it from sibling tools like list_urls_methods or get_status_code_stats, which focus on listing or statistics.
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 by request ID but does not explicitly say when to use this tool versus alternatives like get_request_ids or search_har. The schema's request_id description mentions it can be obtained from list_urls_methods or get_request_ids, which provides context, but the description text itself offers no direct guidance on selecting this tool over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
根据指定 URL 与 HTTP 方法，返回匹配的请求 ID 列表。
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 要过滤的完整请求 URL。通常应与 HAR 中记录的 URL 完全一致。 | |
| method | Yes | 要过滤的 HTTP 方法，例如 GET、POST、PUT、DELETE。 | |
| source | No | 可选 HAR 文件来源。为空时使用默认 HAR；传入时直接分析指定 HAR 文件。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 accurately describes a read-only filtering operation with no harmful side effects, but it does not mention edge cases such as no matches, exact matching rules, or performance implications.
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, front-loaded sentence that efficiently conveys the core function without any extraneous words or redundancy.
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 that an output schema exists and the parameter descriptions are complete, this short description is sufficient for a simple list-returning tool. It could mention the optional source parameter, but the schema already covers that detail, making the overall context adequate.
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 provides detailed descriptions for all three parameters, so the description adds little value beyond restating the roles of URL and method. With 100% schema coverage, the baseline of 3 is appropriate.
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 that the tool returns a list of request IDs filtered by URL and HTTP method. This specific verb+resource combination distinguishes it from sibling tools like get_request_details, which likely focuses on the details of a single request.
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 the tool should be used when you have a specific URL and HTTP method and need to find the corresponding request IDs. However, it does not explicitly mention when to prefer this over siblings or provide any exclusions or alternative tool references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
按 HTTP 状态码汇总请求统计信息。
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | 可选 HAR 文件来源。为空时使用默认 HAR；传入时直接分析指定 HAR 文件。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states the aggregation function and does not disclose whether the tool reads a default HAR, mutates state, or requires prior data loading. This is a minimal disclosure for a read-like stats tool.
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, concise sentence that conveys the core functionality without redundant words or unnecessary 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 stats tool with an output schema and full parameter coverage, the description is minimally adequate. However, it omits contextual details such as the relationship to loaded HAR data (only mentioned in schema) and any step-by-step usage context, leaving some inference to the agent.
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 single 'source' parameter is fully described in the schema (100% coverage), including default behavior and meaning. The tool description adds no extra parameter semantics, so the baseline 3 applies.
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 '汇总' (summarize) and clearly states the resource 'request statistics' grouped by HTTP status code. It distinguishes itself from siblings like get_domain_stats by focusing on status code aggregation.
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 is provided on when to use this tool versus alternatives, nor does it mention prerequisites like needing a loaded HAR. The presence of sibling analysis tools implies possible alternatives, but the description offers no differentiation or usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
列出 HAR 中访问过的所有 URL 与 HTTP 方法组合。
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | 可选 HAR 文件来源。为空时使用 `load_har` 已加载的默认 HAR；传入时直接分析指定 HAR 文件。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden for behavioral disclosure. The description only says what the tool lists but does not mention whether it requires a previously loaded HAR, what happens if none is loaded, or whether it is a safe read-only operation. This is a significant gap for a tool with no annotation support.
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, concise sentence that directly states the tool's function. It is front-loaded with the main action and resource, containing no extraneous words or redundant details.
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's simplicity (one optional parameter, complete schema coverage, and an output schema), the description is mostly sufficient. It clearly states what the tool returns (URL and method combinations). However, it lacks any guidance on when to use this tool relative to its siblings, preventing a perfect score.
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 covers the single 'source' parameter fully, explaining its optionality, default value, and behavior. The tool description adds no parameter-level information, but the schema provides complete semantics, so the baseline of 3 is appropriate.
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 '列出' (list) and clearly identifies the resource as 'URL 与 HTTP 方法组合' (URL and HTTP method combinations). This distinguishes it from sibling tools like get_request_ids or get_domain_stats, making the tool's purpose unambiguous.
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 does not explicitly state when to use this tool versus alternatives like search_har or get_status_code_stats. The intended usage is implied by the purpose, but no clear context or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
从文件路径或 HTTP URL 加载 HAR 文件，并保存为默认分析数据集。
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | HAR 文件来源。支持本地文件绝对/相对路径，或 http/https URL。调用后会把该 HAR 保存为默认分析数据集。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose side effects. It states the tool saves the HAR as the 'default analysis dataset', but does not mention whether it overwrites existing data, validates the HAR format, or handles network authentication for URLs. This lack of behavioral detail is a significant gap for a mutating tool.
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 one sentence, front-loaded with the action ('load HAR'), and contains no filler or redundant information. 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?
The tool is simple with a single fully-described parameter and an output schema. The description covers the core behavior, and the sibling list makes its role clear. However, it would benefit from a note about being a prerequisite for analysis tools, so it is not a 5.
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 provides 100% coverage for the 'source' parameter, including supported path types and the side effect of saving as default dataset. The tool description adds no additional semantic meaning beyond what the schema already documents, so it stays at the baseline.
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 tool 'loads HAR files from file path or HTTP URL and saves as default analysis dataset'. This is a specific verb+resource combination, and it distinguishes itself from the sibling analysis tools (list_urls_methods, get_request_details, etc.) which operate on already-loaded data.
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 context makes it obvious this is the ingestion tool used before analysis tools, since siblings are all query/analysis functions. However, it does not explicitly state 'use this first' or mention exclusions/alternatives, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
在 HAR 中搜索请求头、响应头、请求体和响应体内容。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 要搜索的关键字或片段。可用于匹配请求头、响应头、请求体或响应体中的文本。 | |
| source | No | 可选 HAR 文件来源。为空时使用默认 HAR；传入时直接分析指定 HAR 文件。 | |
| case_sensitive | No | 是否区分大小写。默认 false。 | |
| search_headers | No | 是否搜索请求头与响应头。默认 true。 | |
| search_request_body | No | 是否搜索请求体内容，例如 POST/PUT 的 `postData.text`。默认 true。 | |
| search_response_body | No | 是否搜索响应体内容，例如 `response.content.text`。默认 true。 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden for behavioral disclosure. It does not state whether the operation is read-only (implied by 'search' but not explicit), what the return format is, or how the tool behaves with no matches. It also doesn't describe default toggle states or case sensitivity behavior, leaving these to the schema.
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, front-loaded sentence in Chinese that concisely states the core function and scope. It wastes no words and covers all main search targets in one line.
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?
Despite having 6 parameters, no annotations, and an output schema, the description is minimally sufficient for a search tool. It conveys the essential purpose but leaves gaps: it does not explain how this search tool compares to sibling tools or what the output represents (e.g., matching requests vs. snippets). The schema fills parameter details, and the output schema covers returns, so overall completeness is average.
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 has 100% description coverage for all six parameters, with detailed explanations for query, source, case_sensitive, and the three search toggles. The description does not add any parameter semantics beyond what the schema already provides, so the baseline score of 3 is appropriate.
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 the specific verb 'search' with a clear resource ('HAR') and explicitly lists the four search targets (request headers, response headers, request body, response body). This clearly distinguishes it from sibling tools like list_urls_methods or get_request_details.
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: it is a search tool for finding content within HAR files, which is evident from the verb and the listed targets. However, it does not explicitly state when to prefer this over alternatives, nor does it mention any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.1get_domain_statsget_request_detailsget_request_idsget_status_code_statslist_urls_methodsload_harsearch_harEach tool has a clear, distinct purpose: loading data, listing URL/method combos, filtering request IDs, fetching request details, aggregating by domain or status code, and searching content. No two tools overlap in function.
All tool names follow a consistent verb_noun pattern: load_har, list_urls_methods, get_request_ids, get_request_details, get_domain_stats, get_status_code_stats, search_har. The verbs are uniform and descriptive.
With 7 tools, the set is well-scoped for HAR analysis. Each tool covers a distinct aspect of the workflow, and the count is neither sparse nor bloated.
The surface covers the main HAR analysis workflow: load, browse, filter, inspect, search, and statistics. A minor gap is the absence of a direct 'get all requests' tool, but this can be worked around by combining list_urls_methods with get_request_ids.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
MCP server for AI access to Swagger by SmartBear.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/wdvipa/py-har-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
