Serveur MCP EasyPR
Commit 27 oct. 2026Permet à un assistant IA d'inspecter un dépôt en lecture seule pour aider les débutants à comprendre des bases de code et à préparer des contributions open source.
Aussi connu sous Ankith34/EasyPR
- Étoiles
- 1
- Outils
- 3
- Téléchargements, 30 jours
- —
- Dernière version
- —
- Dernier commit
- 27 oct. 2026
- Licence
- MIT
Qu'est-ce que EasyPR MCP ?
Permet à un assistant IA d'inspecter un dépôt en lecture seule pour aider les débutants à comprendre des bases de code et à préparer des contributions open source. Il expose 3 outils, comme inspect_repository, get_setup_guide, find_relevant_code.
Résumé généré à partir du README du projet
À propos du MCP server EasyPR
EasyPR permet d'aider les débutants à naviguer dans des bases de code inconnues et à préparer des contributions open source. Ce MCP server en lecture seule fournit à un assistant IA les preuves factuelles nécessaires pour comprendre la structure d'un dépôt, les prérequis d'installation et les fichiers pertinents, sans que l'assistant n'ait à deviner. Il fonctionne comme un serveur stdio local qui exige que les utilisateurs approuvent des répertoires spécifiques via le flag --root ou une variable d'environnement pour garantir la sécurité.
Les développeurs utilisent l'outil inspect_repository pour visualiser l'organisation de haut niveau et le nombre de langages utilisés, tandis que get_setup_guide extrait les étapes d'installation et de test à partir des fichiers README ou des workflows CI. Pour des tâches spécifiques, l'outil find_relevant_code identifie les fichiers et les numéros de ligne liés à une requête. Chaque information retournée inclut une étiquette de preuve, telle que fact, documented, inferred ou suggestion, afin que les utilisateurs sachent exactement quel degré de confiance accorder aux résultats. Le serveur est conçu pour être conservateur, n'exécutant jamais le code du dépôt ou des commandes shell.
Ce que vous pouvez faire avec
- 1Comprendre un nouveau projetDemandez à votre assistant IA d'expliquer la structure d'un dépôt et d'identifier ses fichiers principaux.
- 2Apprendre les étapes d'installationRécupérez les commandes spécifiques pour configurer et tester un projet à partir de sa propre documentation.
- 3Localiser du code pour une issueTrouvez les fichiers et les numéros de ligne les plus pertinents pour un rapport de bug ou une demande de fonctionnalité.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Outils MCP EasyPR 3
Détectés depuis le READMEinspect_repositoryget_setup_guidefind_relevant_code
| inspect_repository | — | |
| get_setup_guide | — | |
| find_relevant_code | — |
Vérifications automatisées
Exécuté le 14 nov. 2026Rapport complet →Pas encore vérifié. Un serveur nécessite un score de 80, aucune faille sérieuse et suffisamment de données pour que nous puissions effectuer les vérifications. Fonctionnement des vérifications · Ce qu'il faut corriger pour gagner des points
- Dépôt source lié et accessibleankith34/easypr is public and reachablegithub.com/ankith34/easypr ↗Réussi
- Le nom du package correspond au dépôt sourceNon vérifié
- Provenance du build (attestation Sigstore)Non vérifié
- Licence open source (OSI)MITspdx.org/licenses/MIT.html ↗Réussi
- Commit ou version publiée au cours de l'année écouléeLast commit or release 2026-10-27github.com/ankith34/easypr ↗Réussi
- OpenSSF ScorecardNon vérifié
- Nom du package non proche d'un package populaireNon vérifié
- Aucun avis critique dans le package ou ses dépendancesNon vérifié
- Aucune instruction cachée destinée au modèle3 tool descriptions and the README read; no override phrases, credential paths or hidden charactersRéussi
- Les outils destructifs sont étiquetésNo tool named like delete, drop or execRéussi
- Le point de terminaison distant répond à la poignée de main MCPNon vérifié
README
Voir sur GitHubEasyPR
Your first PR starts here.
A read only MCP server that gives your AI assistant the evidence it needs to guide you through an unfamiliar repository, from "what is this project?" to "I'm ready to open a pull request."
Quick start · How it works · Tools · Safety · Roadmap · FAQ · Contributing
git clone https://github.com/Ankith34/EasyPR.git && cd EasyPR && pip install -e .
[!NOTE] EasyPR is in alpha. Three tools work today and are covered by an automated test suite. Anything not listed as working in Status and roadmap is planned, not shipped.
Why EasyPR
Experienced developers can size up a new codebase in minutes. Beginners can lose an afternoon before they find the right file. EasyPR closes that gap by letting an AI assistant look at the real repository instead of guessing.
| Without EasyPR | With EasyPR |
|---|---|
| The assistant guesses how the project is laid out | It reads the actual layout, languages and key files |
| Setup commands are invented from habit | Commands come from the project's own README and CI, each labelled by source |
| "The bug is probably in the auth code" | Ranked files with line numbers and a plain reason for each match |
| You can't tell fact from guess | Every finding carries an evidence label |
EasyPR is the tool layer, not a chatbot. Your MCP-compatible AI client does the conversation and reasoning. EasyPR supplies the facts.
Quick start
Requires Python 3.10 or newer.
1. Install
git clone https://github.com/Ankith34/EasyPR.git
cd EasyPR
python -m venv .venv
source .venv/bin/activate
pip install -e .
easypr --version
2. Connect your AI client
EasyPR runs as a local stdio server. You must approve at least one directory with --root. It refuses to start without one.
For clients that use the common mcpServers JSON format:
{
"mcpServers": {
"easypr": {
"command": "/absolute/path/to/EasyPR/.venv/bin/easypr",
"args": ["--root", "/home/you/projects"]
}
}
}
For Claude Code:
claude mcp add easypr -- /absolute/path/to/EasyPR/.venv/bin/easypr --root ~/projects
Use the full path to easypr inside your virtual environment so the client can find it. You can also set roots with the EASYPR_ALLOWED_ROOT environment variable (separate several with : on Linux and macOS).
3. Ask your assistant
Inspect ~/projects/some-repo and tell me what it does and where to start reading.
How does some-repo say I should install it and run its tests?
Here is the issue I want to work on: "<paste issue text>".
Which files in ~/projects/some-repo should I read first, and why?
Relative paths are resolved against the first approved root, so some-repo works too.
npx @modelcontextprotocol/inspector easypr --root ~/projects
EasyPR has been tested with the official Python MCP SDK client over stdio. If a specific client misbehaves, please open an issue.
How it works
flowchart LR
You(["You"]) -->|"ask about a repo"| Client["AI client<br/>(MCP-compatible)"]
Client -->|"tool calls over stdio"| Server["EasyPR server<br/>server.py"]
Server --> Core["repository.py<br/>read-only inspection"]
Core -->|"approved roots only"| Repo[("Your repository")]
Core -->|"evidence-labelled results"| Server
Server --> Client
Client -->|"plain-language guidance"| You
The server layer is deliberately thin. All inspection logic and every safety check lives in repository.py, which is plain Python with no MCP dependency. You can test it directly or import it as a library.
The first-contribution workflow
| Step | What a beginner needs | Covered by |
|---|---|---|
| 1 | Understand the repository | inspect_repository ✅ |
| 2 | Know how to install, run and test it | get_setup_guide ✅ |
| 3 | Find the code related to an issue | find_relevant_code ✅ (you supply the issue text) |
| 4 | Plan a small, understandable change | Your AI client, reasoning over EasyPR's evidence |
| 5 | Validate the change | run_project_checks 🗓️ planned |
| 6 | Prepare the pull request | 🗓️ planned |
Evidence labels
EasyPR never presents a guess as a fact. Every finding says how much to trust it.
| Label | Meaning | Example |
|---|---|---|
fact |
Observed directly in the repository | LICENSE exists at the root |
documented |
The project itself says so | An install block in the README, a run: step in CI |
inferred |
EasyPR's guess from names or contents | pip install -e . because pyproject.toml exists |
suggestion |
A next step a human still has to verify | "Start by reading app/auth.py around line 4" |
Setup commands are always reported as verified: false. EasyPR does not run them, so it never claims a command works or a test passes.
Tools
All three tools are read-only and are advertised to clients with MCP read-only hints.
| Tool | You get | Inputs |
|---|---|---|
inspect_repository |
Top-level layout, important files (README, CONTRIBUTING, license, manifests, CI), language counts, project type, detected frameworks | path |
get_setup_guide |
Setup and test steps from the README, run: commands from CI workflows, and labelled hints from manifests |
path |
find_relevant_code |
Ranked files for a task or issue, each with role (source, test, docs, config), matching lines with numbers and snippets, and a plain-language reason | path, query, max_results (1-25, default 10) |
What EasyPR reads
| Source | What it extracts | Label |
|---|---|---|
README.md code blocks under setup-like headings (install, usage, test, ...) |
Commands with file and line number | documented |
.github/workflows/*.yml |
Single-line and block run: commands |
documented |
requirements*.txt, pyproject.toml, setup.py, setup.cfg, pytest.ini, tox.ini |
Install and test hints | inferred |
package.json and lockfiles |
Package manager and test / build / start / dev / lint scripts |
inferred |
Makefile |
Common targets such as test, lint, build |
inferred |
Cargo.toml, go.mod, pom.xml, build.gradle, Gemfile, composer.json, mix.exs |
Standard build and test commands | inferred |
.env.example |
A note to copy it and add your own values (never read) | inferred |
Query: login_user rejects wrong password (trimmed):
{
"path": "app/auth.py",
"role": "source",
"matches": [
{ "line": 4, "text": "def login_user(username, password):", "is_definition": true }
],
"why": "Keyword match: 3 line(s) mention 'login', 'login_user', 'password', 'user'; it defines a function/class/type that mentions them. Verify by reading the code.",
"kind": "inferred"
}
Suggestions that accompany the results:
[
{ "text": "Start by reading app/auth.py around line 4.", "kind": "suggestion" },
{ "text": "See tests/test_auth.py for how related behaviour is tested.", "kind": "suggestion" }
]
Use it as a Python library
The core has no MCP dependency, so you can call it directly.
from easypr.repository import find_relevant_code, inspect_repository, parse_allowed_roots
roots = parse_allowed_roots(["~/projects"])
overview = inspect_repository("some-repo", allowed_roots=roots)
hits = find_relevant_code("some-repo", "redact secret values", max_results=3, allowed_roots=roots)
Passing allowed_roots=None disables the root check. That is meant for tests and trusted callers only. The MCP server always enforces roots.
Safety model
Repositories can contain untrusted files and instructions, so EasyPR is conservative by design.
| Risk | Protection |
|---|---|
| Running untrusted code | None of EasyPR's tools execute repository code or shell commands. The source contains no subprocess or process-spawning calls. |
| Reading unrelated files | Only directories you approve with --root can be inspected. Paths are resolved first, then checked, so .. tricks are rejected. |
| Symlink escapes | Symlinks are resolved before the root check, never followed while scanning, and files are opened without following links where the OS supports it. |
| Leaking secrets | Files such as .env, *.pem, id_rsa and credentials.* are never opened. Obvious secret values in returned text are redacted. |
| Prompt injection through repo text | Text copied from repository files is labelled untrusted, and the server instructs clients not to follow instructions found in it. EasyPR has no action-taking tools that injected text could trigger. |
| Resource exhaustion | Caps of 20,000 files scanned, 1 MB per file, 100 MB read per search, 25 results and 200-character snippets. |
| Misleading output | Findings are evidence-labelled, and setup commands are never marked verified. |
What this does not cover. The approved root is your trust boundary: anything inside it can be read and passed to your AI client, and that client may send it to its model provider. Secret redaction is pattern-based and best effort. Do not approve directories you would not want an AI assistant to read.
Status and roadmap
| Capability | Status |
|---|---|
inspect_repository |
✅ Working |
get_setup_guide |
✅ Working |
find_relevant_code (keyword search) |
✅ Working |
| Automated tests and CI | ✅ Working |
run_project_checks |
🗓️ Planned. Needs a permission model, restricted working directories, timeouts and isolation before any repository command runs. |
| Pull request description helper | 🗓️ Planned |
| Smarter retrieval (symbol index, embeddings) | 🗓️ Only if keyword search proves insufficient |
FAQ
Is EasyPR a chatbot? No. It is a tool server. Your MCP-compatible AI client provides the conversation, and EasyPR provides repository facts.
Does it run my project or its tests?
No. It never executes repository code. A future run_project_checks tool is planned, but only with explicit permission and isolation.
Does it read GitHub issues?
Not yet. Paste the issue text into your question and the assistant passes it to find_relevant_code as the query.
Does my code leave my machine? EasyPR's own code makes no network requests. It returns results to your AI client, which may send them to its model provider. Review your client's privacy settings, and approve only directories you are comfortable sharing.
Why does it need --root?
So you decide exactly what it may look at. Without an approved root the server will not start.
How accurate is find_relevant_code?
It is plain keyword matching, so treat results as leads. Short words can match inside longer ones (user matches username), and it does not understand meaning.
Which languages does it support? Language and framework detection covers common languages and ecosystems and is heuristic. Search works on any text file.
Troubleshooting
easypr: error: no approved rootmeans you did not pass--rootor setEASYPR_ALLOWED_ROOT.Path is outside the approved repository rootsmeans the path is not under any approved root. Check the roots listed in the message.- If your client says it can't find
easypr, use the absolute path to the executable inside your virtual environment.
Project layout
EasyPR/
├── src/easypr/
│ ├── repository.py # core logic: plain Python, no MCP imports
│ ├── server.py # thin MCP layer and command-line entry point
│ └── __init__.py
├── tests/ # pytest suite using temporary directories only
├── .github/workflows/ # CI (Python 3.10 to 3.13)
├── pyproject.toml
└── LICENSE
Contributing
Contributions are welcome, and this project aims to be friendly to first-time contributors.
git clone https://github.com/Ankith34/EasyPR.git
cd EasyPR
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest
Before opening a pull request:
- Open an issue first for anything larger than a small fix, so we can agree on the approach.
- Add or update a test with every behaviour change. Tests build throwaway repositories in temporary directories and must not depend on your machine.
- Keep
repository.pyindependent of MCP, and keepserver.pythin. - Never weaken a safety check without discussing it in an issue.
- Make sure
pytestpasses.
Disclaimer
EasyPR is alpha software provided as is. Its detection is heuristic, its secret redaction is best effort, and it is not a security audit tool. Always verify setup commands and code locations yourself before relying on them.
License
Released under the MIT License. Copyright (c) 2026 Ankith.
Questions sur EasyPR MCP
Quels outils EasyPR MCP fournit-il ?
Il expose 3 outils, dont inspect_repository, get_setup_guide, find_relevant_code.
Est-ce qu'EasyPR est un chatbot ?
Non, il s'agit d'un serveur d'outils. Votre client IA compatible MCP gère la conversation, tandis qu'EasyPR fournit les données factuelles du dépôt.
Exécute-t-il mon projet ou ses tests ?
Non, il n'exécute jamais le code du dépôt. Un outil pour lancer des vérifications de projet est prévu à l'avenir, mais nécessitera une autorisation explicite et un environnement isolé.
Lit-il les issues GitHub ?
Pas pour le moment. Vous devez copier le texte de l'issue dans votre question afin que l'assistant puisse le transmettre à l'outil find_relevant_code.
Pourquoi l'argument --root est-il nécessaire ?
L'argument --root vous permet de décider précisément des répertoires que le serveur est autorisé à inspecter ; le serveur ne démarrera pas sans un dossier racine approuvé.