Mathematical Code Execution MCP server
Commit Nov 13, 2026Executes sandboxed Python code to perform mathematical calculations and generate one-page PDF documents.
Also known as Saify-Technologies/saifs-ai-mcps-docs, code-execution
- Stars
- 4
- Tools
- 1
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Mathematical Code Execution MCP?
Mathematical Code Execution executes sandboxed Python code to perform mathematical calculations and generate one-page PDF documents. It exposes 1 tool, such as execute_code.
Summary generated from the project's README
About Mathematical Code Execution MCP server
Performing complex mathematical computations and generating PDF documents from within an AI client is what this server enables. It provides a remote, sandboxed environment that executes Python code through a streamable HTTP transport. Developers using Claude Desktop, VS Code, or Claude Code can connect to the endpoint without local installation, though they must complete an OAuth 2.1 PKCE sign-in process on their first use.
The execution environment is strictly isolated with no network access, no user filesystem, and no ability to install new packages. While it supports numpy for matrix operations and statistical calculations, it does not include scipy or pandas. The primary tool, execute_code, returns standard output, error messages, and exit codes. If the code uses the preinstalled fpdf library to create a one-page PDF, the server provides a download link that remains active for one hour.
What you can do with it
- 1Statistical Data AnalysisAsk the AI to calculate the mean and standard deviation of a specific dataset using Python.
- 2Matrix MultiplicationRequest a numpy script to multiply two matrices and display the resulting product.
- 3Automated Document GenerationHave the agent create a one-page PDF invoice summary and provide a temporary download link.
Written from the project's README. Every use case is checked against a quote from it.
How to install Mathematical Code Execution MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Mathematical Code Execution MCP in Claude Code
$ claude mcp add --transport http code-execution https://code-execution-mcp.saifs.ai/mcpInstall Mathematical Code Execution MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"code-execution": {
"url": "https://code-execution-mcp.saifs.ai/mcp"
}
}
}Install Mathematical Code Execution MCP in VS Code
.vscode/mcp.json
{
"servers": {
"code-execution": {
"type": "http",
"url": "https://code-execution-mcp.saifs.ai/mcp"
}
}
}Install Mathematical Code Execution MCP in VS Code CLI
$ code --add-mcp '{"name":"code-execution","type":"http","url":"https://code-execution-mcp.saifs.ai/mcp"}'Install Mathematical Code Execution MCP in Codex
$ codex mcp add code-execution --url https://code-execution-mcp.saifs.ai/mcpInstall Mathematical Code Execution MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.code-execution] url = "https://code-execution-mcp.saifs.ai/mcp"
Install Mathematical Code Execution MCP in Gemini CLI
$ gemini mcp add -s user --transport http code-execution https://code-execution-mcp.saifs.ai/mcpInstall Mathematical Code Execution MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"code-execution": {
"url": "https://code-execution-mcp.saifs.ai/mcp",
"type": "http"
}
}
}Mathematical Code Execution MCP tools 1
Detected from the READMEexecute_code
| execute_code | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesaify-technologies/saifs-ai-mcps-docs is public and reachablegithub.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model1 tool description and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubMathematical Code Execution
A Python-only sandbox for agent hosts. The model writes Python that prints a result (or a one-page PDF via preinstalled fpdf); this server runs it in an isolated process with no network, no user filesystem and no package installs. Other languages are refused. numpy is available; scipy and pandas are not.
| Registry name | ai.saifs/code-execution |
| Endpoint | https://code-execution-mcp.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-code-execution": {
"type": "http",
"url": "https://code-execution-mcp.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://code-execution-mcp.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-code-execution https://code-execution-mcp.saifs.ai/mcp
Any other MCP client
Point it at https://code-execution-mcp.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
execute_code |
Runs allow-listed Python and returns stdout, stderr, exit code, and any PDF written with fpdf (output("name.pdf"), download link expires in 1 hour). Non-Python is rejected with a one-line warning. |
Example prompts
- “Run Python to compute the mean and standard deviation of this list and print the result.”
- “Write a short numpy snippet that multiplies these two matrices and prints the product.”
- “Generate a one-page PDF invoice summary with fpdf and give me the download link.”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Mathematical Code Execution MCP questions
How do I add Mathematical Code Execution MCP to Claude Code?
Run claude mcp add --transport http code-execution https://code-execution-mcp.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Mathematical Code Execution MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Mathematical Code Execution MCP provide?
It exposes 1 tool, including execute_code.
What programming languages are supported?
The server only supports Python; all other languages are refused.
Which Python libraries are available?
Numpy is available, but scipy and pandas are not included.
Can the server generate PDF files?
Yes, it can generate a one-page PDF using the preinstalled fpdf library.
Does the code execution have network access?
No, the code runs in an isolated process with no network access and no user filesystem access.