mcpField
A
AgentTasker MCP Server

AgentTasker MCP Server

Local
github.com/S3bRRAI & Agents
Repository

About AgentTasker MCP Server

AgentTasker MCP Server is a local stdio MCP server for running web searches, webpage reads, and configured MCP tool calls concurrently. It is aimed at agents that need batched work, with background jobs, caching, and rate limiting.

Key features

  1. 01Run searches and webpage reads in parallel
  2. 02Batch calls to configured MCP tools
  3. 03Track or cancel background batches
  4. 04Cache searches and limit request rates

Use cases

  1. 01Search several topics concurrently
  2. 02Read multiple webpages in one batch
  3. 03Run repeated MCP tool calls together

MCP support

It exposes tools for executing and managing batches, and can connect to other configured MCP servers through its own stdio connections. Web search requires a configured provider; webpage fetching works without an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "s3brr-agent-tasker": {
      "command": "uvx",
      "args": [
        "agent-tasker-mcp-server"
      ]
    }
  }
}
Run commanduvx agent-tasker-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiagent-tasker-mcp-server1.0.1

Tools

2

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
urlstringNoTarget URL
bodystringNoRequest body
codestringNoPython code
modeenumNow or aw | a
namestringNoTask name
pathstringNoFile path
querystringNoSearch query
methodenumNoHTTP methodDELETE | GET | HEAD | OPTIONS | PATCH | POST | PUT
commandstringNoCommand
contentstringNoFile content
headersobjectNoHeaders
retriesintegerNoRetry count
timeoutintegerNoTimeout seconds
max_linksintegerNoMax links
providersarrayNoDiscovery providers
task_typeenumYesTask typepython_code | http_request | discovery_search | web_scrape | shell_command | file_read | file_write
verify_sslbooleanNoVerify SSL
max_resultsintegerNoMax results
output_modeenumNofull or compactfull | compact
include_htmlbooleanNoInclude raw HTML
extract_linksbooleanNoInclude links
max_body_bytesintegerNoMax response bytes
max_text_charsintegerNoMax extracted chars
fetch_max_charsintegerNoChars per fetched page
extract_headingsbooleanNoInclude headings
fetch_top_resultsintegerNoFetch top result pages
link_include_patternstringNoRegex for kept links
retry_backoff_secondsintegerNoRetry backoff seconds

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.