How do I use AgentTasker MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AgentTasker MCP Server run Python code and an HTTP request in parallel" 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.

AgentTasker MCP Server

by S3bRR

Overview Schema Related Servers Score Discussions

Python

Local

AgentTasker MCP Server

AgentTasker is a small, stdio-only MCP server for AI agents that need to run multiple tasks quickly and get structured results back in one call.

It is intentionally narrow:

two tools: execute and execute_batch
local stdio transport only
zero third-party runtime dependencies
explicit dependency control with depends_on
compact, model-friendly JSON responses

Repository: https://github.com/S3bRR/agent-tasker-mcp

Why This Exists

Most agent orchestration layers are heavier than they need to be. This project is designed for the common case:

run a few tasks in parallel
let one task wait on another when needed
keep the MCP surface small enough for models to use reliably

There is no queue service, no persistence layer, no background worker system, and no SDK dependency required at runtime.

Related MCP server: local-mcp

What It Supports

Task types:

python_code
http_request
discovery_search
web_scrape
shell_command
file_read
file_write

Public MCP tools:

execute
execute_batch

Install

Requirements:

Python 3.10+
A local MCP client that can run stdio servers

Recommended: `uvx`

Run directly from GitHub:

uvx --from git+https://github.com/S3bRR/agent-tasker-mcp.git agent-tasker-mcp-server --workers 8

Once the package is live on PyPI, the command becomes:

uvx agent-tasker-mcp-server --workers 8

`pipx`

Install directly from GitHub:

pipx install git+https://github.com/S3bRR/agent-tasker-mcp.git

Once the package is live on PyPI, the command becomes:

pipx install agent-tasker-mcp-server

Local clone

git clone https://github.com/S3bRR/agent-tasker-mcp.git
cd agent-tasker-mcp
./setup.sh

setup.sh creates a local .venv, installs this package into it, and prints an absolute MCP config snippet. If python3 -m venv is not available, it falls back to virtualenv when installed.

MCP Client Configuration

GitHub Source

{
  "command": "uvx",
  "args": [
    "--from",
    "git+https://github.com/S3bRR/agent-tasker-mcp.git",
    "agent-tasker-mcp-server",
    "--workers",
    "8"
  ]
}

Installed Package

{
  "command": "agent-tasker-mcp-server",
  "args": ["--workers", "8"]
}

Local checkout

{
  "command": "/absolute/path/to/agent-tasker-mcp/.venv/bin/agent-tasker-mcp-server",
  "args": ["--workers", "8"]
}

Use the exact absolute path printed by ./setup.sh for local checkouts.

Usage

`execute`

Run one task immediately.

{
  "task_type": "python_code",
  "code": "result = 6 * 7"
}

`execute_batch`

Run multiple tasks concurrently.

{
  "tasks": [
    {
      "name": "fetch_users",
      "task_type": "http_request",
      "url": "https://api.example.com/users"
    },
    {
      "name": "calc",
      "task_type": "python_code",
      "code": "result = 6 * 7"
    }
  ],
  "output_mode": "compact"
}

`depends_on`

If one task must wait for another, make it explicit.

{
  "tasks": [
    {
      "name": "write_file",
      "task_type": "file_write",
      "path": "/tmp/example.txt",
      "content": "hello"
    },
    {
      "name": "read_file",
      "task_type": "file_read",
      "path": "/tmp/example.txt",
      "depends_on": ["write_file"]
    }
  ]
}

If an upstream dependency fails, downstream tasks are marked failed and do not run.

Output Shape

output_mode supports:

compact (default)
full

The response is ordered to match the input task list, which makes it easier for models to consume without extra reconciliation logic.

Release Process

Releases are tag-driven.

update pyproject.toml and server.json to the same version
commit and push to main
create and push a matching tag such as v1.0.0
GitHub Actions runs tests, builds the package, publishes to PyPI through Trusted Publishing, and then publishes server.json to the MCP Registry

The release workflow rejects version drift: the pushed tag, pyproject.toml, and server.json must match exactly.

Limits

Optional environment variables:

AGENT_TASKER_MAX_TASKS: maximum tasks per execute_batch
AGENT_TASKER_MAX_PAYLOAD_BYTES: maximum payload size per task
AGENT_TASKER_MAX_MEMORY_MB: soft process memory guard

Security Notes

This server is intended for trusted environments.

python_code executes Python code
shell_command executes shell commands
file_read and file_write operate on the local filesystem

Do not expose this server directly to untrusted users.

Development

Create a local environment:

./setup.sh
source .venv/bin/activate

Run the server:

agent-tasker-mcp-server --workers 4

Run tests:

.venv/bin/python -m unittest discover -s tests

Packaging

This repo includes server.json for MCP Registry publication and a GitHub Actions workflow that publishes both the PyPI package and MCP metadata from a version tag.

License

MIT

Available Tools

2 tools

executeB

Run one task and return its result.

ParametersJSON Schema

Name	Required	Description	Default
`name`	No	Task name
`task_type`	Yes	Task type
`code`	No	Python code
`timeout`	No	Timeout seconds
`url`	No	Target URL
`method`	No	HTTP method
`headers`	No	Headers
`body`	No	Request body
`verify_ssl`	No	Verify SSL
`max_body_bytes`	No	Max response bytes
`retries`	No	Retry count
`retry_backoff_seconds`	No	Retry backoff seconds
`query`	No	Search query
`providers`	No	Discovery providers
`max_results`	No	Max results
`fetch_top_results`	No	Fetch top result pages
`fetch_max_chars`	No	Chars per fetched page
`max_links`	No	Max links
`max_text_chars`	No	Max extracted chars
`include_html`	No	Include raw HTML
`extract_links`	No	Include links
`extract_headings`	No	Include headings
`link_include_pattern`	No	Regex for kept links
`command`	No	Command
`path`	No	File path
`content`	No	File content
`mode`	No	w or a
`output_mode`	No	full or compact	compact

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, and the description adds no behavioral context beyond the basic action. It does not disclose security requirements, side effects, rate limits, or error handling, leaving a significant gap for a tool with 28 parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (6 words) and front-loaded with the core purpose. However, for a tool with 28 parameters, slightly more detail could aid understanding without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high parameter count and no output schema, the description is insufficiently complete. It lacks information about return values, error scenarios, and how to properly configure the many task types.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add any meaning beyond the schema's parameter descriptions, which are already present.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Run one task and return its result' clearly states the action (run) and the resource (task), and implicitly distinguishes from sibling 'execute_batch' by specifying a single task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 execute_batch, or on prerequisites, context, or exclusions. The agent must infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute_batchA

Run many tasks in parallel and return ordered results.

ParametersJSON Schema

Name	Required	Description	Default
`tasks`	Yes	Task definitions
`output_mode`	No	full or compact	compact

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but only mentions parallelism and ordered results. It omits details on error handling, concurrency limits, side effects, or ordering guarantees. Some transparency exists but significant gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence covering the core functionality without redundancy. It is appropriately front-loaded, though it could benefit from a brief expansion on ordering or parallelism details without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (multiple task types, no output schema, no annotations), the description is too brief. It fails to explain ordering guarantees, error behavior, return structure, or concurrency limits, leaving the agent with insufficient context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema for the 'tasks' and 'output_mode' parameters, which are already well-documented in the input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'run[s] many tasks in parallel' and returns ordered results, distinguishing it from the sibling 'execute' tool which likely handles single tasks. The verb 'run' and resource 'tasks' are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for parallel execution of multiple tasks via the phrase 'many tasks in parallel,' which contrasts with the sibling 'execute' tool for single tasks. However, it does not explicitly state when to use this tool over alternatives or provide exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

2 tool updatesv1.0.1Jun 4, 2026
- First observedexecute
- First observedexecute_batch

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0

Disambiguation5/5

The two tools have clearly distinct purposes: one executes a single task, the other executes multiple tasks in parallel. There is no overlap or ambiguity.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern: 'execute' and 'execute_batch'. The batch suffix clearly indicates the parallel execution variant.

Tool Count3/5

With only 2 tools, the server feels minimal. While it covers the basic task execution needs, the scope of a 'Tasker' service might warrant additional tools for management (e.g., listing, canceling). The count is borderline but acceptable for a narrow focus.

Completeness2/5

The server lacks tools for task management beyond execution, such as listing tasks, checking status, canceling, or deleting. This creates significant gaps for an agent needing full task lifecycle support.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp-serverOAuth
com.niftypm
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Project Management Communication File Systems
2
KodyOAuth
io.github.kentcdodds
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
Developer Tools Code Execution Command Line
2514
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
microservices.sh
sh.microservices
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Cloud Platforms Agent Orchestration Developer Tools
21

Related MCP Servers

nexus-mcp
Autonomous Agents Agent Orchestration Developer Tools
j7an
A
license
A
quality
A
maintenance
MCP server that lets AI models invoke CLI agents (Gemini, Codex, Claude, OpenCode) as tools — with parallel execution, retries, and structured output parsing.
Updated a day ago (2026-09-05 08:01 UTC)
5
4
MIT
local-mcp
File Systems Shell Access
fan-67
A
license
Not graded
quality
C
maintenance
A lightweight, stdio-based MCP server enabling AI assistants to perform local file system operations like reading, writing, searching, and executing commands.
Updated 3 months ago (2026-06-14 18:37 UTC)
5,122
MIT
mcp-sidecar
Shell Access Command Line Developer Tools
lsequeiraa
A
license
Not graded
quality
C
maintenance
A lightweight, cross-platform MCP server for managing background processes. Enables AI coding agents to spawn, monitor, and interact with long-lived processes.
Updated a month ago (2026-08-01 08:16 UTC)
MIT
Nockit MCP
Developer Tools Command Line Monitoring
codeCrack-01
A
license
A
quality
B
maintenance
A lightweight MCP server that enables AI assistants to execute local development tools and retrieve system status with low latency over stdio or HTTP.
Updated a month ago (2026-08-05 15:42 UTC)
1
84
3
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/S3bRR/agent-tasker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

AgentTasker MCP Server

Why This Exists

What It Supports

Install

Recommended: uvx

pipx

Local clone

MCP Client Configuration

GitHub Source

Installed Package

Local checkout

Usage

execute

execute_batch

depends_on

Output Shape

Release Process

Limits

Security Notes

Development

Packaging

License

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

nexus-mcp

local-mcp

mcp-sidecar

Nockit MCP

Latest Blog Posts

MCP directory API

Recommended: `uvx`

`pipx`

`execute`

`execute_batch`

`depends_on`