MCP Tool Integration · Public

dspy

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

Best fitDevelopers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.

Check whether this project matches your task before installing it.

What it can doMCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot34k stars

2.9k forks · 425 contributors

Official first step Read manual preview Source repository

Publication status · 2026-05-20

What is dspy?

dspy helps connect external tools, services, or data sources to AI hosts that support MCP.
Best fit: Developers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.
Not for: Not for users who cannot change host configuration, grant tool permissions, or isolate network, file, and credential access.
Capability added to an AI workflow: MCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks
First safe verification step: Verify the MCP server command, permission scope, and rollback path in a non-primary host configuration first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: The main risk is unclear tool, filesystem, network, or credential boundaries contaminating host configuration or exposing sensitive data.
Evidence base: https://github.com/stanfordnlp/dspy, https://github.com/stanfordnlp/dspy#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers who need Claude, Cursor, Codex, or another MCP-capable AI host to call external tools safely.

Match the project to your task before installing it.

CapabilityMCP setup guidance, host configuration checks, tool permission boundaries, recovery steps, and acceptance checks

MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.

Repositorystanfordnlp/dspy

34k stars · 2.9k forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Introduction to DSPy

Related topics: Installation and Setup, Core Architecture

Sources: [README.md:1]()

Installation and Setup

Related topics: Introduction to DSPy, Language Model Clients

Sources: [CONTRIBUTING.md]()

Core Architecture

Related topics: Signatures System, Module System

Sources: [dspy/primitives/example.py:1-50]()

Signatures System

Related topics: Core Architecture, Prediction Modules

Sources: [dspy/signatures/signature.py:1-50]()

Module System

Related topics: Core Architecture, Prediction Modules

Sources: [dspy/primitives/module.py:1-50]()

Sources: https://github.com/stanfordnlp/dspy, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars34k stars

Forks2.9k forks

Contributors425 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using dspy with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
PythonInterpreter: paths containing commas are silently misparsed by Den
github / github_issue
02
[Bug] PythonInterpreter fails with default setup due to missing Deno rea
github / github_issue
03
Use Tool functions that require external libaries in CodeAct
github / github_issue
04
3.2.1
github / github_release
05
3.2.0
github / github_release
06
3.1.3
github / github_release
07
3.1.2
github / github_release
08
3.1.1
github / github_release
09
3.1.0
github / github_release
10
3.1.0b1
github / github_release
11
3.0.4
github / github_release
12
3.0.4b2
github / github_release

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install dspy

Official start command · https://github.com/stanfordnlp/dspy#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

dspy Manual

DSPy (Declarative Self-Improving Language Model Programs) is a Python framework that compiles declarative language model calls into self-improving pipelines. The installation process suppo...

Open the full manual

dspy Human Manual
Table of Contents
Introduction to DSPy
Related Pages
Core Philosophy
Key Concepts
Signatures
Modules

Introduction to DSPy

Related topics: Installation and Setup, Core Architecture

Sources: [README.md:1]()

Installation and Setup

Related topics: Introduction to DSPy, Language Model Clients

Sources: [CONTRIBUTING.md]()

Core Architecture

Related topics: Signatures System, Module System

Sources: [dspy/primitives/example.py:1-50]()

Signatures System

Related topics: Core Architecture, Prediction Modules

Sources: [dspy/signatures/signature.py:1-50]()

Module System

Related topics: Core Architecture, Prediction Modules

Sources: [dspy/primitives/module.py:1-50]()

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start ManifestPROJECT_PACK.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.