What can you do with this server?

This server provides secure, remote backend computation for AI agents, with x402 USDC microtransactions per API call. Capabilities include: * execute_code_securely: Execute arbitrary Python code in an isolated Azure sandbox. Returns stdout/stderr (up to 8KB). Cost: 0.10 USDC. * sanitize_csv_securely: Clean and normalize raw CSV strings, handling nulls (NaN → null), normalizing headers, and dropping empty rows. Returns a JSON array. Cost: 0.25 USDC. * optimize_ga_securely: Run a Genetic Algorithm to optimize model parameters (polynomial, exponential, logistic) against numerical data, minimizing MAPE. Supports configurable generations. Returns optimized parameters and MAPE. Cost: 0.50 USDC. * generate_plot_securely: Generate line or scatter charts from coordinate arrays, with customizable titles and labels. Returns a base64-encoded image string. Cost: 0.30 USDC.

How do I use agentic-compute-mcp?

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., "@agentic-compute-mcp Optimize my sales forecast using genetic algorithm" 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.

agentic-compute-mcp

by codelad1304

Overview Schema Related Servers Score Discussions

Python

Remote

agentic-compute-mcp

mcp-name: io.github.codelad1304/agentic-compute

LLM Context Summary: agentic-compute-mcp is a secure Model Context Protocol (MCP) server providing premium backend computation for autonomous AI agents. It offers remote Python code execution, CSV data sanitization, Genetic Algorithm optimization, and base64 Matplotlib visualization. It utilizes the x402 protocol on the Base network for automated USDC microtransactions per API call.

🖼️ Zero-Context Image Rendering Handling base64 image strings in LLM context windows is notoriously unreliable and eats up thousands of tokens. agentic-compute-mcp solves this locally. When you call generate_plot, the Azure sandbox generates the chart and streams the payload back to the MCP client. The client automatically intercepts the payload, decodes it, and saves it directly to your local machine as optimized_load_trend.png—completely bypassing the LLM context window to prevent token exhaustion and transcription errors.

System Prompt Instructions (For Developers)

Copy and paste this snippet into your agent's system prompt or .cursorrules file to enable autonomous tool usage:

You are equipped with the `agentic-compute-mcp` backend. Use these tools for heavy computation or secure data execution. 
- You must pay for invocations automatically using the configured x402 EVM private key.
- Do NOT attempt to run Python locally if data requires complex optimization; route it to `execute_code`.
- For any unformatted CSV data, run `sanitize_csv` before performing mathematical analysis.
- When generating charts, use `generate_plot`. The backend will automatically save the chart directly to the local file system as a PNG. Do not attempt to read base64 strings.

Related MCP server: code-sandbox-mcp

Available MCP Tools

This server exposes the following endpoints. Agents must evaluate the required capability and cost before invoking.

execute_code

Cost: 0.10 USDC / call

Input: Valid Python script string.

Output: Text (stdout/stderr). Max return limit is 8KB.

When to use: Use to execute arbitrary Python logic, heavy calculations, or data sorting in an isolated Azure sandbox. Do NOT use for local file system operations.

sanitize_csv

Cost: 0.25 USDC / call

Input: Raw, unformatted CSV string.

Output: JSON array.

When to use: Use immediately on raw data sets to handle null values (converts NaN to null), normalize headers, and drop empty rows prior to modeling.

optimize_ga

Cost: 0.50 USDC / call

Input: JSON array of numerical data.

Output: Optimized model parameters and MAPE score.

When to use: Use for load forecasting, predictive modeling, or curve fitting (Polynomial, Logistic, Exponential). Employs proportional mutation for <1% MAPE accuracy.

generate_plot

Cost: 0.30 USDC / call

Input: JSON array of coordinates/data points and chart configuration.

Output: Success string (File saved locally).

When to use: Use to visualize data without hitting token generation limits or requiring local GUI dependencies.

Installation & Setup

Install via PyPI:

pip install agentic-compute-mcp-codelad1304

Configure Environment Variables:

You must provide a funded EVM wallet key to allow your agent to process x402 microtransactions.

export EVM_PRIVATE_KEY=your_private_key_here

Client Configuration (Claude Desktop)

To install this server for Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "agentic-compute": {
      "command": "agentic-compute-mcp",
      "args": [],
      "env": {
        "EVM_PRIVATE_KEY": "your_private_key_here"
      }
    }
  }
}

License

MIT License - see LICENSE file for details.

Available Tools

4 tools

execute_code_securelyA

Executes Python code in a remote, isolated Azure sandbox environment with automatic x402 payment handling.

Use this tool to safely evaluate Python algorithms, process data structures, perform math calculations, or run custom scripts.

Usage Guidelines:

Code must be standard Python 3.
Script execution is subject to a 30-second timeout limit; avoid infinite loops or blocking operations.
Ensure all required imports are included within the snippet.
x402 micropayments (USDC on Base) are automatically verified per execution call.

ParametersJSON Schema

Name	Required	Description	Default
`code`	Yes	A complete, self-contained Python 3 code string to execute within the remote sandbox environment.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses the isolated sandbox environment, timeout limit, and automatic payment handling, which are key behavioral traits. It could optionally mention error handling or return format, but it already provides significant transparency for a code execution tool.

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

Conciseness5/5

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

The description is well-structured with a concise opening sentence, a short use-case paragraph, and a bulleted guideline list. Every sentence earns its place; there is no redundancy or fluff.

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

Completeness4/5

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

For a code execution tool with a single parameter and output schema present, the description covers purpose, environment, timeouts, imports, and payment behavior. It omits return-value details but the presence of an output schema reasonably handles that. It is complete enough for an agent to select and invoke correctly.

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?

The schema description covers 100% of the single parameter, so baseline is 3. The description reinforces the need for self-contained code with imports included, but this is more of an instruction than new parameter semantics. It does not add syntax, format, or edge-case detail beyond the 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 action ('Executes Python code'), the resource ('remote, isolated Azure sandbox environment'), and distinguishes it from sibling tools that target specific use cases like CSV sanitization or plot generation. It also lists concrete use cases, leaving no ambiguity about what the tool does.

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?

A dedicated 'Usage Guidelines' section provides explicit context for when to use the tool (evaluate algorithms, process data, math, custom scripts) and important constraints (standard Python 3, 30-second timeout, imports included, x402 payments). It does not name alternatives or exclusions, but the guidance is clear and actionable.

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

generate_plot_securelyA

Generate line or scatter charts from x and y data in an isolated Azure sandbox, enabling secure remote data visualization for AI agents.

ARCHITECTURE NOTE: The remote sandbox generates the plot, but the local MCP client intercepts the base64 payload and securely writes it directly to the user's local home directory as a PNG.

Use this tool to visually represent numerical trends. Keep data arrays under 10,000 points to prevent sandbox timeouts.

ParametersJSON Schema

Name	Required	Description	Default
`x`	Yes	A list of numerical values for the X-axis. Must be the exact same length as y.
`y`	Yes	A list of numerical values for the Y-axis. Must be the exact same length as x.
`title`	No	The text string to display at the top of the chart.	Data Plot
`x_label`	No	The text string to label the X-axis.	X
`y_label`	No	The text string to label the Y-axis.	Y
`chart_type`	No	The visual style of the chart. Must be exactly 'line' or 'scatter'.	line

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.1/5.0

Behavior4/5

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 explains the isolated Azure sandbox, the local interception of the base64 payload, and the secure writing of the PNG to the user's home directory. This is considerable transparency, though it does not detail file naming or overwrite behavior.

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 efficient and well-structured, leading with the core purpose and adding an architecture note. It is slightly longer than necessary but each sentence adds meaningful value, and the guidance is front-loaded.

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

Completeness4/5

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

Given the tool's moderate complexity, the description covers purpose, usage, security architecture, output location, and size constraints. An output schema exists, so return values are not needed. Minor gaps like file naming do not detract significantly from overall completeness.

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 the schema already documents each parameter. The description adds the array size limit (under 10,000 points) and clarifies the x/y data relationship, but does not significantly enhance parameter semantics beyond the 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 'Generate line or scatter charts from x and y data', specifying both the action and resource. It effectively distinguishes this tool from siblings like execute_code_securely and sanitize_csv_securely by focusing on plot generation.

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 says 'Use this tool to visually represent numerical trends', providing contextual guidance for when to use it. It also includes a practical constraint about keeping data arrays under 10,000 points to avoid timeouts, but does not explicitly mention alternatives or 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.

optimize_ga_securelyA

Executes a Genetic Algorithm in a secure remote Azure sandbox to minimize Mean Absolute Percentage Error (MAPE) against ground-truth target values.

Ideal for driving down error metrics in complex time-series predictions, such as electrical load forecasting.

Usage Guidelines:

actuals array size must not exceed 5,000 data points to prevent sandbox execution timeouts.
generations should be kept under 1,000 iterations for optimal performance vs. compute cost.
model_type is strictly limited to 'polynomial', 'exponential', or 'logistic'.

ParametersJSON Schema

Name	Required	Description	Default
`actuals`	Yes	A list of numerical float values representing the ground-truth targets to optimize against.
`model_type`	No	The underlying curve model to fit during optimization.	polynomial
`generations`	No	The integer number of evolutionary generations the algorithm should iterate through.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the behavioral transparency burden. It discloses the sandboxed secure execution environment, timeout risks, and performance/compute trade-offs via the given constraints. It does not describe error behavior or output details, but the output schema covers return structure.

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

Conciseness5/5

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

The description is concise and well-structured: a one-sentence purpose, a short ideal-use case, and a bulleted list of guidelines. Every sentence contributes value with no redundancy or fluff.

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

Completeness4/5

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

The tool is moderately complex, with 3 params, an output schema, and security/sandbox context. The description covers purpose, use case, and key constraints, making it fairly complete. It does not detail the GA internals or failure modes, but these are non-essential given the schema and scope.

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

Parameters4/5

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

While the input schema already covers all parameters (100% coverage), the description adds meaningful constraints beyond the schema: actuals size limit (5000), generations upper bound (1000), and confirmation of strict model_type enum. This enriches the agent's understanding of practical invocation limits.

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 explicitly states the tool 'Executes a Genetic Algorithm in a secure remote Azure sandbox to minimize Mean Absolute Percentage Error (MAPE)' against ground-truth targets. This specific verb-resource pair clearly distinguishes it from sibling tools like 'execute_code_securely' or 'generate_plot_securely'.

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 provides a clear use case ('Ideal for driving down error metrics in complex time-series predictions') and specific operational limits (e.g., actuals ≤ 5000, generations < 1000). However, it does not explicitly mention alternative tools or exclusion scenarios, missing the 'when-not-to-use' guidance.

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

sanitize_csv_securelyA

Sanitize raw CSV data by cleaning and normalizing it within a secure remote Azure sandbox environment.

Use this tool to prepare messy tabular data for downstream processing. It automatically strips leading/trailing whitespace, standardizes delimiters to commas, and resolves malformed rows.

Usage Guidelines:

csv_content must be a plain-text string representation of a CSV.
Limit payload size to a maximum of 50,000 rows to prevent sandbox memory limits and payload timeouts.
Do not pass binary files or Excel (.xlsx) formats; strictly text-based CSV data.

ParametersJSON Schema

Name	Required	Description	Default
`csv_content`	Yes	The raw, unformatted CSV text string that requires cleaning.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

No annotations are present, so the description carries the full burden. It discloses specific cleaning behaviors ('strips leading/trailing whitespace, standardizes delimiters to commas, and resolves malformed rows') and sandbox-related constraints ('secure remote Azure sandbox environment', 'sandbox memory limits and payload timeouts'). This gives good insight into side effects and limitations, though it doesn't detail the output format (covered by output schema).

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

Conciseness5/5

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

The description is efficiently structured: a clear opening sentence, a one-sentence purpose, and a bulleted list of usage guidelines. No redundant information; every sentence adds value.

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

Completeness5/5

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

Given the tool's simplicity (one parameter), a complete schema, and an output schema, the description covers all necessary aspects: purpose, when to use, constraints, and behavioral specifics. It is a well-rounded description for this tool's complexity.

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

Parameters4/5

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

Schema description coverage is 100% for csv_content, so baseline is 3. The description adds meaning by specifying that csv_content 'must be a plain-text string representation of a CSV' and reiterates the text-only requirement, which supplements the schema description 'raw, unformatted CSV text string that requires cleaning.'

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?

Description clearly identifies the tool's function: 'Sanitize raw CSV data by cleaning and normalizing it within a secure remote Azure sandbox environment.' This uses a specific verb+resource (sanitize CSV) and the 'Use this tool to prepare messy tabular data' phrase further clarifies intent. It is distinct from sibling tools like execute_code_securely or generate_plot_securely.

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?

Provides explicit usage context: 'Use this tool to prepare messy tabular data for downstream processing' and includes concrete when-not constraints like 'Do not pass binary files or Excel (.xlsx) formats; strictly text-based CSV data.' However, it does not name alternative tools for cases where a different tool would be appropriate, 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.

Tool Schema Changelog

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

4 tool updatesv1.1.4Aug 8, 2026

Changedexecute_code_securely1 field changed

addedInput schema / properties / code / description

Added value: +"A complete, self-contained Python 3 code string to execute within the remote sandbox environment."

Changedgenerate_plot_securely6 fields changed

addedInput schema / properties / chart_type / description

Added value: +"The visual style of the chart. Must be exactly 'line' or 'scatter'."

addedInput schema / properties / title / description

Added value: +"The text string to display at the top of the chart."

addedInput schema / properties / x / description

Added value: +"A list of numerical values for the X-axis. Must be the exact same length as y."

addedInput schema / properties / x_label / description

Added value: +"The text string to label the X-axis."

addedInput schema / properties / y / description

Added value: +"A list of numerical values for the Y-axis. Must be the exact same length as x."

addedInput schema / properties / y_label / description

Added value: +"The text string to label the Y-axis."

Changedoptimize_ga_securely3 fields changed

changedInput schema / properties / actuals / description

Previous value: -"Sequence of ground-truth target values to optimize against."New value: +"A list of numerical float values representing the ground-truth targets to optimize against."

changedInput schema / properties / generations / description

Previous value: -"Number of GA iterations/generations to run (default: 200)."New value: +"The integer number of evolutionary generations the algorithm should iterate through."

changedInput schema / properties / model_type / description

Previous value: -"Optimization curve model ('polynomial', 'exponential', or 'logistic')."New value: +"The underlying curve model to fit during optimization."

Changedsanitize_csv_securely1 field changed
- addedInput schema / properties / csv_content / description
```
Added value: +"The raw, unformatted CSV text string that requires cleaning."
```

4 tool updatesv1.1.1Aug 6, 2026
- First observedexecute_code_securely
- First observedgenerate_plot_securely
- First observedoptimize_ga_securely
- First observedsanitize_csv_securely

Install Server

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

TDQS

A4.4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: generic code execution, CSV sanitization, genetic algorithm optimization, and plotting. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow the consistent pattern of verb_object_securely (e.g., execute_code_securely, generate_plot_securely). This makes the set predictable and easy to navigate.

Tool Count5/5

With 4 tools, the set is well-scoped and each tool earns its place. The count is within the ideal 3-15 range and matches the server's focus on secure remote compute tasks.

Completeness4/5

The code execution tool provides a general catch-all capability, and the specialized tools cover data cleaning, optimization, and visualization. Minor gaps exist (e.g., no generic data transformation tool), but the core workflows are covered without dead ends.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

mcp A
com.everstake
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Blockchain Cryptocurrency
1111
sovereign-engine A
io.github.invertedhoologan
15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server.
AI & Machine Learning Payments & Billing Cryptocurrency
2
AgentLot Marketplace C
io.agentlot
AI marketplace for agents to find paid work and trade digital services via MCP and x402.
E-commerce & Retail Payments & Billing
1241
mcpOAuth
ai.agentgates
Confidential compute and inference sold to agents over x402 USDC, plus an agent wallet over MCP.
AI & Machine Learning Blockchain Cryptocurrency
1

Related MCP Servers

opendexterofficial
Payments & Billing Cryptocurrency
Dexter-DAO
A
license
Not graded
quality
C
maintenance
An MCP server that enables AI agents to search, pay for, and call paid APIs using the x402 protocol, with automatic USDC settlement.
Updated a day ago (2026-09-05 01:39 UTC)
2
MIT
code-sandbox-mcp
Code Execution Shell Access
feifeigood
A
license
A
quality
D
maintenance
MCP server for E2B code sandbox, enabling creation, management, and execution of code in secure sandboxes using Python and shell commands.
Updated 8 months ago (2026-01-05 06:10 UTC)
4
1
MIT
@easynodexyz/mcp-x402
Cloud Platforms Blockchain Cryptocurrency
easynodexyz
A
license
A
quality
D
maintenance
MCP server enabling AI agents to purchase VPS and blockchain node products using USDC on Base via Easy Node's x402 API.
Updated 7 months ago (2026-02-02 12:11 UTC)
7
15
7
Business Source 1.1
mcp-python-exec-sandbox
Code Execution Developer Tools
lu-zhengda
A
license
A
quality
D
maintenance
Sandboxed Python execution with automatic dependency management. Executes Python scripts in isolated environments (bubblewrap or Docker) with PEP 723 inline dependencies, preventing host pollution.
Updated 7 months ago (2026-02-09 05:45 UTC)
3
1
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/codelad1304/agentic-compute-mcp'

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

agentic-compute-mcp

System Prompt Instructions (For Developers)

Available MCP Tools

Installation & Setup

Configure Environment Variables:

Client Configuration (Claude Desktop)

License

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

opendexterofficial

Latest Blog Posts

MCP directory API