SkillAgentSearch skills...

anysearch-mcp-server

Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction.

Install / Use

claude mcp add anysearch-ai -- npx -y github:anysearch-ai/anysearch-mcp-server

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

94/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of anysearch-mcp-server

anysearch-mcp-server scores 94/100 on our quality scale, 66th of 326 Customer Support skills we index (top 21%).

Its MCP Server is 17 KB long, well organised into 25 sections with 16 code examples: a thorough specification that gives an agent plenty to work with.

With 2,057 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so anysearch-mcp-server is actively maintained.
  • Our last check on 2026-10-21 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-25. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

anysearch-mcp-server compared with similar skills

All 4 of these similar skills score higher than anysearch-mcp-server; compare them before choosing.

SkillScoreStarsUpdatedFormat
anysearch-mcp-server (this skill)by anysearch-ai942.1k49d agoMCP Server
Agent-Reachby Panniantong100109.2ktodayCLAUDE.md
headroomby headroomlabs-ai10078.9ktodayCLAUDE.md
CowAgentby zhayujie10047.8ktodayCLAUDE.md
Scraplingby D4Vinci10097.9ktodayMCP Server

Frequently asked questions

How do I install anysearch-mcp-server?
Run claude mcp add anysearch-ai -- npx -y github:anysearch-ai/anysearch-mcp-server. The install tabs above show the steps for each supported agent.
Which AI agents does anysearch-mcp-server work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is anysearch-mcp-server safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is anysearch-mcp-server still maintained?
The repository was last updated about 2 months ago, so anysearch-mcp-server is actively maintained.

AnySearch MCP Server

English | 简体中文

Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction.

Features

  • General Web Search — open-ended natural language queries
  • Vertical Domain Search — structured queries across finance, academic, security, legal, code, and more
  • Parallel Batch Search — execute multiple independent queries in one call
  • URL Content Extraction — fetch and extract full page content as Markdown
  • Anonymous Access — works without an API key (with lower rate limits)

API Key Configuration

An API key is optional but recommended. Without a key, all features still work via anonymous access with lower rate limits.

Register for an API Key (Recommended)

The agent can register the user and obtain an API key in a single call — no verification code, no manual signup. Ask the user for a real email address: it becomes the account username.

curl -s -X POST "https://api.anysearch.com/v1/auth/email/register" \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'

Success response (code: 0) returns the account info and a one-time plaintext API key:

{
  "code": 0,
  "message": "success",
  "data": {
    "username": "you@example.com",
    "email": "you@example.com",
    "login_url": "https://www.anysearch.com/login",
    "api_key": {
      "id": "key_xxxxxxxx",
      "key": "as_sk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
      "key_prefix": "as_sk_xxxxxx...",
      "name": "default",
      "rate_limit": 100,
      "quota_limit": 0,
      "expires_at": null,
      "created_at": "2026-06-23T10:23:00Z"
    }
  }
}

Quota fields such as rate_limit are account-specific response values; do not treat the example as a fixed plan.

On success the agent MUST:

  1. Put data.api_key.key into the MCP server config as the Authorization: Bearer <key> value (and/or set ANYSEARCH_API_KEY) — it is shown only once (it can also be retrieved later from the dashboard).
  2. Tell the user their username (= email) and the login_url.

Errors can be expressed through the HTTP status, application-level code, or message; do not assume every error uses code: -1:

| status / code / message | what to do | | ----------------------- | ---------- | | Invalid email address. | ask the user to re-enter the email | | HTTP 409 or email_already_registered | email is taken — tell the user to sign in at login_url; do not retry | | code: 42901, rate_limited, or contains Rate limited | prefer a retry delay from Retry-After, response data, or the message; if none is provided, stop repeated requests and retry later or use anonymous access | | starts with Key creation failed. | account created but key failed — extract the email and URL from the message ("Key creation failed. Your account <email> was created; sign in at <url>.") and tell the user to sign in there to create a key manually | | Internal server error. | retry later or fall back to anonymous |

The email must be real and reachable.

Get an API Key

Alternatively, visit https://anysearch.com/console/api-keys to create a free API key.

Key Priority

| Priority | Source | |----------|--------| | 1 (highest) | --api_key CLI flag / Authorization header | | 2 | Environment variable ANYSEARCH_API_KEY | | 3 | .env file (ANYSEARCH_API_KEY=<key>) | | 4 | Anonymous access (lower rate limits) |

Key Behavior

| Scenario | Behavior | |----------|----------| | No key | Proceed with anonymous access (lower rate limits) | | Has key | Sent via Authorization: Bearer <key> header, higher rate limits | | Key exhausted, auto-registered key returned | Agent should ask user for confirmation, then persist the new key | | Key exhausted, no new key | Inform user and suggest configuring a new API key |

MCP Transport

The production endpoint is:

https://api.anysearch.com/mcp

It natively uses Streamable HTTP. Current OpenCode, Claude Code, Cursor, VS Code, Cline, OpenAI Codex, Google Antigravity, DeepSeek Harness, Hermes Agent, and OMP releases can connect to it directly; no SSE or stdio proxy is needed. The configurations below follow each client's current official documentation.

Installation

The API key is optional. Where a client documents environment-variable or secret storage for custom headers, the examples use the recommended authenticated setup. Where it does not, the example stays anonymous and explains how to add authentication only in private user configuration. To use anonymous access elsewhere, remove only the Authorization entry and keep X-Anysearch-Client.

OpenCode

Official docs: MCP servers and configuration locations.

Use ~/.config/opencode/opencode.json for a global configuration or opencode.json in the project root. On Windows, the global path is %USERPROFILE%\.config\opencode\opencode.json.

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "anysearch": {
      "type": "remote",
      "url": "https://api.anysearch.com/mcp",
      "enabled": true,
      "oauth": false,
      "headers": {
        "Authorization": "Bearer {env:ANYSEARCH_API_KEY}",
        "X-Anysearch-Client": "mcp/1.0.0"
      }
    }
  }
}

OpenCode uses {env:NAME} for environment-variable substitution. "oauth": false prevents an unnecessary OAuth discovery flow for this API-key-authenticated server.

After saving, run opencode mcp list and confirm that anysearch is shown as connected.

Claude Code

Official docs: Connect Claude Code to tools via MCP.

For a private, user-wide installation, run:

claude mcp add --transport http anysearch https://api.anysearch.com/mcp --scope user --header 'Authorization: Bearer ${ANYSEARCH_API_KEY}' --header 'X-Anysearch-Client: mcp/1.0.0'

The user scope stores the server in ~/.claude.json and makes it available across all projects on the machine. Single quotes preserve the variable reference so the plaintext key is not written to the config; set ANYSEARCH_API_KEY before starting Claude Code. For anonymous access, omit the Authorization --header option.

For a shareable project configuration, create .mcp.json in the project root:

{
  "mcpServers": {
    "anysearch": {
      "type": "http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ANYSEARCH_API_KEY}",
        "X-Anysearch-Client": "mcp/1.0.0"
      }
    }
  }
}

Claude Code expands ${VAR} and ${VAR:-default} in .mcp.json, including inside url and headers. Set ANYSEARCH_API_KEY before starting Claude Code. Project-scoped servers require approval when first opened interactively.

Verify the connection with:

claude mcp get anysearch
claude mcp list

Inside Claude Code, /mcp shows the server status and available tools.

Cursor

Official docs: Model Context Protocol.

Use .cursor/mcp.json for a project or ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "anysearch": {
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:ANYSEARCH_API_KEY}",
        "X-Anysearch-Client": "mcp/1.0.0"
      }
    }
  }
}

Cursor automatically recognizes the remote HTTP endpoint and supports ${env:NAME} interpolation in url and headers.

Check the connection under Customize > MCPs or Output > MCP Logs. If Cursor CLI is installed, you can also run:

agent mcp list
agent mcp list-tools anysearch

VS Code

Official docs: Add and manage MCP servers and MCP configuration reference.

Run MCP: Open User Configuration for a user-wide server, or create .vscode/mcp.json in a workspace. This example uses a password input so the key is prompted for and stored securely instead of being committed:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "anysearch-api-key",
      "description": "AnySearch API key",
      "password": true
    }
  ],
  "servers": {
    "anysearch": {
      "type": "http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${input:anysearch-api-key}",
        "X-Anysearch-Client": "mcp/1.0.0"
      }
    }
  }
}

For anonymous access, remove the Authorization entry and the entire inputs array.

Run MCP: List Servers, select anysearch, then choose Start or Show Output to verify the connection. Note that ${input:...} works in local VS Code, but servers requiring interactive input are not forwarded to Agent Host. For configurations shared with Agent Host or other Copilot tools, use a workspace .mcp.json or user ~/.copilot/mcp-config.json and avoid interactive inputs.

Cline

Official docs: MCP.

In the Cline panel, open MCP Servers > Configure > Configure MCP Servers, or add a hosted endpoint from the Remote Servers tab. Use the explicit streamableHttp type; omitting it falls back to legacy SSE behavior.

{
  "mcpServers": {
    "anysearch": {
      "type": "streamableHttp",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:ANYSEARCH_API_KEY}",
        "X-Anysearch-Client": "mcp/1.0.0"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Cline IDE supports ${env:VAR} in url, headers, and env. Run cline mcp to open the CLI wizard, or cline config mcp --json to list the configuration. The official web docs still name ~/.cline/mcp.json, while the current source defaults to ~/.cline/data/settings/cline_mcp_settings.json; use Configure MCP Servers in the IDE or the CLI wizard to open the effective file instead of relying on a hard-coded path.

The following five entries were checked against first-party configuration documentation on 2026-08-27. This establishes documented client compatibility, not a local end-to-end connection certification.

OpenAI Codex

Official docs: Model Context Protocol.

Use ~/.codex/config.toml globally or .codex/config.toml in a trusted project. The Codex CLI, IDE extension, and desktop app share this configuration:

[mcp_servers.anysearch]
url = "https://api.anysearch.com/mcp"
bearer_token_env_var = "ANYS…[redacted]"
http_headers = { "X-Anysearch-Client" = "mcp/1.0.0" }

Set ANYSEARCH_API_KEY before starting Codex. For anonymous access, remove bearer_token_env_var. Run codex mcp list, or use /mcp inside the Codex TUI, to confirm the server and its tools are available.

Google Antigravity

Official docs: MCP servers in Antigravity.

Use ~/.gemini/config/mcp_config.json globally or .agents/mcp_config.json in a workspace. Remote servers must use serverUrl; the legacy url and httpUrl keys are not supported:

{
  "mcpServers": {
    "anysearch": {
      "serverUrl": "https://api.anysearch.com/mcp",
      "headers": {
        "X-Anysearch-Client": "mcp/1.0.0"
      }
    }
  }
}

Antigravity's official documentation currently shows literal custom-header values but does not document environment-variable interpolation for remote headers. If authentication is required, add "Authorization": "Bearer YOUR_API_KEY" only to the private global file and never commit it to .agents/mcp_config.json. Open MCP Servers > Manage MCP Servers in the IDE, or run /mcp in the CLI, to inspect live status, logs, and tools.

DeepSeek Harness

Official sources: [De

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars2.1k
CategoryCustomer
Updated1mo ago
Forks187

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions