HikerAPI

io.github.subzeroidv1.1.2更新于 Oct 6, 2026

Instagram data via HikerAPI: profiles, posts, reels, stories, comments, hashtags, locations.

已验证STDIO仅桌面Web Search & ScrapingData & Analytics

概览

AI 生成的概览

让助手通过 HikerAPI 查询 Instagram 数据：个人资料、帖子、Reels、快拍、评论、话题标签和地点。

功能
启动时根据 HikerAPI 的 OpenAPI 规范生成 MCP 工具，把每个只读 GET 端点映射为一个工具，例如 get_v2_user_by_username 或 get_v2_hashtag_medias_recent。默认核心集提供约 44 个精选工具，每个任务一个，并带有说明用途、分页和计费的手写描述。设置 HIKERAPI_TOOLS=all 可暴露所有未弃用的端点（100 个以上）。响应以原始 JSON 文本返回，非 2xx 响应会作为工具错误呈现。
适用场景
适合助手需要 Instagram 个人资料、帖子、Reels、快拍、评论、话题标签或地点数据用于研究、监测或内容分析的场景。如果你已有 HikerAPI 访问权限，并希望助手直接调用这些端点而不必自己写 API 代码，就值得添加。
运行要求
通过 stdio 在本地运行，通常使用 npx hikerapi-mcp，因此需要 Node.js。需要在 HIKERAPI_KEY 环境变量中提供 HikerAPI 访问密钥，并以 x-access-key 请求头发送。需要访问 api.hikerapi.com 的网络连接，并在启动时获取 OpenAPI 规范。可选变量可控制基础 URL、工具集、标签过滤、超时和响应大小限制。
安装前请注意
HIKERAPI_KEY 是计费凭据：请求会消耗你的 HikerAPI 配额或额度，免费额度有限。如果 HIKERAPI_URL 指向默认主机以外的地址，密钥会被发送到该主机，服务器会在启动时发出警告。所有工具均为只读，但返回的数据涉及第三方 Instagram 账号，请按适用规则处理。

安装

在 SourceWeft 中

  1. 打开 控制台中的 HikerAPI，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

hikerapi-mcp

[npm version] [npm downloads] [License: MIT]

MCP server for HikerAPI — Instagram data API. Available on npm: hikerapi-mcp.

Generates MCP tools from the HikerAPI OpenAPI spec at startup. HikerAPI only exposes read (GET) endpoints — each tool maps 1:1 to one of them (GET /v2/user/by/username → get_v2_user_by_username). By default you get a core set of ~45 tools, one per task, each with a description that tells the assistant when to use it; HIKERAPI_TOOLS=all exposes every non-deprecated endpoint (100+).

Get 100 Free API Requests

Sign up with this link and get 100 free HikerAPI requests — no credit card required. Enough to wire up the MCP server, try a few prompts in Claude/Cursor/Codex, and evaluate the data quality before committing.

Get your free 100 requests here

Quick start

  1. Get an API key at hikerapi.com/tokens.
  2. Add the server to your AI assistant.
  3. Ask your assistant something like:
    • "Get the Instagram profile for @nasa."
    • "Find the top 5 recent posts under the hashtag #photography."
    • "Show stories for the user with id 25025320."

Claude Code

bash
claude mcp add hikerapi -e HIKERAPI_KEY=your-api-key -- npx -y hikerapi-mcp

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "hikerapi": {      "command": "npx",      "args": ["-y", "hikerapi-mcp"],      "env": {        "HIKERAPI_KEY": "your-api-key"      }    }  }}

Cursor / Windsurf

Same shape as Claude Desktop — put the block under mcpServers in the app's MCP config file.

Zed

Add to ~/.config/zed/settings.json:

json
{  "context_servers": {    "hikerapi": {      "command": "npx",      "args": ["-y", "hikerapi-mcp"],      "env": {        "HIKERAPI_KEY": "your-api-key"      }    }  }}

OpenAI Codex

Append to ~/.codex/config.toml:

toml
[mcp_servers.hikerapi]command = "npx"args = ["-y", "hikerapi-mcp"]
[mcp_servers.hikerapi.env]HIKERAPI_KEY = "your-api-key"

Tools

Tools are generated at startup from the live HikerAPI OpenAPI spec.

HikerAPI has 100+ GET endpoints, and most of them are version variants of the same call (v1 / v2 / gql / g2). Handing all of them to an assistant makes it pick the wrong one, so the default core set keeps one endpoint per task:

GroupToolsExamples
Profiles16get_v2_user_by_username, get_gql_user_medias, get_g2_user_followers
Posts, comments, likers8get_v2_media_info_by_url, get_v2_media_comments, get_v2_media_likers
Search7get_v2_fbsearch_accounts, get_v2_fbsearch_reels, get_v1_search_hashtags
Hashtags4get_v2_hashtag_medias_top, get_v2_hashtag_medias_recent
Locations3get_g2_location_by_id, get_v1_location_medias_recent_chunk
Stories, highlights, links5get_v2_story_by_url, get_v2_highlight_by_id, get_v1_share_by_url
Audio1get_v2_track_by_id

Core tools carry hand-written descriptions (what the tool does, when to prefer a sibling, pagination, billing) and every tool is annotated read-only. The list lives in src/curated.ts.

Set HIKERAPI_TOOLS=all to expose every non-deprecated endpoint instead — same tool names as before, so existing prompts keep working. Tool names mirror their endpoint (GET /v2/user/by/username → get_v2_user_by_username); call tools/list over MCP for the current list with parameter schemas. Legacy and System groups are excluded in both modes.

Configuration

VariableDescriptionRequired
HIKERAPI_KEYYour HikerAPI access key (sent as x-access-key header)yes
HIKERAPI_URLBase URL. Default: https://api.hikerapi.com (alias https://api.instagrapi.com)no
HIKERAPI_SPEC_URLOpenAPI spec URL. Default: ${HIKERAPI_URL}/openapi.jsonno
HIKERAPI_TOOLScore (default): curated set, one tool per task. all: every non-deprecated endpointno
HIKERAPI_TAGSWhitelist: only include operations with these tags (comma-separated)no
HIKERAPI_EXCLUDE_TAGSBlacklist: additional tags to exclude (on top of default Legacy,System)no
HIKERAPI_TIMEOUT_MSPer-request timeout for API calls. Default: 30000no
HIKERAPI_SPEC_TIMEOUT_MSTimeout for the startup spec fetch. Default: 60000no
HIKERAPI_SPEC_RETRY_DELAY_MSBase delay between the 3 startup spec fetch attempts. Default: 2000no
HIKERAPI_MAX_RESPONSE_BYTESMax bytes read from each API response. Default: 10485760 (10 MB)no
HIKERAPI_MAX_SPEC_BYTESMax bytes read from the OpenAPI spec. Default: 8388608 (8 MB)no

Legacy and System tags are excluded by default. Deprecated operations are also skipped.

If HIKERAPI_URL points to a host other than api.hikerapi.com or api.instagrapi.com, the server prints a warning on startup — your key will be sent there, so only use it for a self-hosted or proxied HikerAPI.

Requests are sent with User-Agent: hikerapi-mcp/<version>.

Example — expose every endpoint of the most common groups:

json
"env": {  "HIKERAPI_KEY": "...",  "HIKERAPI_TOOLS": "all",  "HIKERAPI_TAGS": "User Profile,Post Details,Search,Hashtags,Stories"}

How it works

AI Assistant ←stdio→ hikerapi-mcp ──https──> api.hikerapi.com                          │                          └─ fetches /openapi.json once on startup,                             builds one MCP tool per GET endpoint                             (core set by default)

Tool arguments map to the endpoint's query and path parameters. The response body is returned as-is (JSON text). Non-2xx responses are surfaced as tool errors with the HTTP status and body.

Development

bash
git clone https://github.com/subzeroid/hikerapi-mcp.gitcd hikerapi-mcpnpm installnpm run buildHIKERAPI_KEY=your-key node dist/index.js

Run in watch mode:

bash
HIKERAPI_KEY=your-key npm run dev

Run tests (unit + stdio smoke tests against a local mock server, no network/API key required):

bash
npm test

License

MIT

来源：README.md，提交 0ca4b6a

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v1.1.2最新Oct 6, 2026