cf-mcp-orange 1.0.1__tar.gz

cf_mcp_orange-1.0.1/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: cf-mcp-orange
+Version: 1.0.1
+Summary: A complete Codeforces MCP toolset for AI agents
+Author-email: supriya <supriya81205@gmail.com>
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: fastmcp>=0.1.2
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: beautifulsoup4>=4.12.0
+
+# cpmcp-oren 🚀
+
+[![PyPI version](https://img.shields.io/pypi/v/cpmcp-oren)](https://pypi.org/project/cpmcp-oren/)
+
+A **complete, all-in-one MCP (Model Context Protocol) server** for Codeforces. 
+Designed to supercharge AI coding assistants like **Cline** and **Claude Desktop**.
+
+---
+
+## ✨ Features (10 Powerful Tools)
+
+1. **`get_user`** – Fetch a detailed profile (rating, max rating, last 5 contests, problem stats by difficulty, top 10 categories).
+2. **`compare_user`** – Side-by-side comparison of two Codeforces users.
+3. **`get_problemlist`** – Search the entire problemset by rating range, topic tags (`AND`/`OR`), and sorting.
+4. **`get_problem`** – Retrieve the full problem statement, rating, and tags for any specific contest/problem ID.
+5. **`get_practiceproblems`** – Identify a user's weakest core topics and recommend 3 targeted problems within `+300` rating.
+6. **`get_random_practice`** – A completely random problem within `+/- 300` of a user's current rating.
+7. **`get_upsolve`** – Analyzes a user's last 10 contests and recommends unsolved problems within their rating range.
+8. **`get_status`** – Summarizes the last 1000 submissions (AC/WA/TLE counts) and the 20 most recent attempts.
+9. **`get_catalog`** – Searches and fetches the latest official educational articles from the Codeforces Catalog.
+10. **`submit_solution`** – (*Optional*) Submits code to a problem via the authenticated API.
+
+---
+
+## 🛠️ Installation & Configuration (No Keys Required!)
+
+You don't need to clone or manually install anything! Just add this to your `cline_mcp_settings.json` or `mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "cpmcp-oren": {
+      "command": "uvx",
+      "args": ["cpmcp-oren"]
+    }
+  }
+}

cf_mcp_orange-1.0.1/README.md

@@ -0,0 +1,37 @@
+# cpmcp-oren 🚀
+
+[![PyPI version](https://img.shields.io/pypi/v/cpmcp-oren)](https://pypi.org/project/cpmcp-oren/)
+
+A **complete, all-in-one MCP (Model Context Protocol) server** for Codeforces. 
+Designed to supercharge AI coding assistants like **Cline** and **Claude Desktop**.
+
+---
+
+## ✨ Features (10 Powerful Tools)
+
+1. **`get_user`** – Fetch a detailed profile (rating, max rating, last 5 contests, problem stats by difficulty, top 10 categories).
+2. **`compare_user`** – Side-by-side comparison of two Codeforces users.
+3. **`get_problemlist`** – Search the entire problemset by rating range, topic tags (`AND`/`OR`), and sorting.
+4. **`get_problem`** – Retrieve the full problem statement, rating, and tags for any specific contest/problem ID.
+5. **`get_practiceproblems`** – Identify a user's weakest core topics and recommend 3 targeted problems within `+300` rating.
+6. **`get_random_practice`** – A completely random problem within `+/- 300` of a user's current rating.
+7. **`get_upsolve`** – Analyzes a user's last 10 contests and recommends unsolved problems within their rating range.
+8. **`get_status`** – Summarizes the last 1000 submissions (AC/WA/TLE counts) and the 20 most recent attempts.
+9. **`get_catalog`** – Searches and fetches the latest official educational articles from the Codeforces Catalog.
+10. **`submit_solution`** – (*Optional*) Submits code to a problem via the authenticated API.
+
+---
+
+## 🛠️ Installation & Configuration (No Keys Required!)
+
+You don't need to clone or manually install anything! Just add this to your `cline_mcp_settings.json` or `mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "cpmcp-oren": {
+      "command": "uvx",
+      "args": ["cpmcp-oren"]
+    }
+  }
+}

cf_mcp_orange-1.0.1/cf_mcp_orange.egg-info/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: cf-mcp-orange
+Version: 1.0.1
+Summary: A complete Codeforces MCP toolset for AI agents
+Author-email: supriya <supriya81205@gmail.com>
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: fastmcp>=0.1.2
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: beautifulsoup4>=4.12.0
+
+# cpmcp-oren 🚀
+
+[![PyPI version](https://img.shields.io/pypi/v/cpmcp-oren)](https://pypi.org/project/cpmcp-oren/)
+
+A **complete, all-in-one MCP (Model Context Protocol) server** for Codeforces. 
+Designed to supercharge AI coding assistants like **Cline** and **Claude Desktop**.
+
+---
+
+## ✨ Features (10 Powerful Tools)
+
+1. **`get_user`** – Fetch a detailed profile (rating, max rating, last 5 contests, problem stats by difficulty, top 10 categories).
+2. **`compare_user`** – Side-by-side comparison of two Codeforces users.
+3. **`get_problemlist`** – Search the entire problemset by rating range, topic tags (`AND`/`OR`), and sorting.
+4. **`get_problem`** – Retrieve the full problem statement, rating, and tags for any specific contest/problem ID.
+5. **`get_practiceproblems`** – Identify a user's weakest core topics and recommend 3 targeted problems within `+300` rating.
+6. **`get_random_practice`** – A completely random problem within `+/- 300` of a user's current rating.
+7. **`get_upsolve`** – Analyzes a user's last 10 contests and recommends unsolved problems within their rating range.
+8. **`get_status`** – Summarizes the last 1000 submissions (AC/WA/TLE counts) and the 20 most recent attempts.
+9. **`get_catalog`** – Searches and fetches the latest official educational articles from the Codeforces Catalog.
+10. **`submit_solution`** – (*Optional*) Submits code to a problem via the authenticated API.
+
+---
+
+## 🛠️ Installation & Configuration (No Keys Required!)
+
+You don't need to clone or manually install anything! Just add this to your `cline_mcp_settings.json` or `mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "cpmcp-oren": {
+      "command": "uvx",
+      "args": ["cpmcp-oren"]
+    }
+  }
+}

cf_mcp_orange-1.0.1/cf_mcp_orange.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+cf_mcp_orange.egg-info/PKG-INFO
+cf_mcp_orange.egg-info/SOURCES.txt
+cf_mcp_orange.egg-info/dependency_links.txt
+cf_mcp_orange.egg-info/requires.txt
+cf_mcp_orange.egg-info/top_level.txt
+src/cpmcp_oren/__init__.py
+src/cpmcp_oren/__main__.py

cf_mcp_orange-1.0.1/cf_mcp_orange.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cf_mcp_orange-1.0.1/cf_mcp_orange.egg-info/requires.txt

@@ -0,0 +1,3 @@
+fastmcp>=0.1.2
+httpx>=0.27.0
+beautifulsoup4>=4.12.0

cf_mcp_orange-1.0.1/cf_mcp_orange.egg-info/top_level.txt

@@ -0,0 +1 @@
+cpmcp_oren

cf_mcp_orange-1.0.1/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cf-mcp-orange"
+version = "1.0.1"
+description = "A complete Codeforces MCP toolset for AI agents"
+readme = "README.md"
+authors = [{name = "supriya", email = "supriya81205@gmail.com"}]
+license = {text = "MIT"}
+requires-python = ">=3.10"
+dependencies = [
+    "fastmcp>=0.1.2",
+    "httpx>=0.27.0",
+    "beautifulsoup4>=4.12.0"
+]
+
+[tool.setuptools]
+packages = ["cpmcp_oren"]
+package-dir = {"cpmcp_oren" = "src/cpmcp_oren"}

cf_mcp_orange-1.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cf_mcp_orange-1.0.1/src/cpmcp_oren/__init__.py

@@ -0,0 +1,303 @@
+from fastmcp import FastMCP
+
+# Import your tool logic from the 'tools' package (Relative imports)
+from .tools.get_user import fetch_and_parse_user_data
+from .tools.compare_user import compare_users_data
+from .tools.get_problemlist import get_filtered_problems
+from .tools.get_problem import get_problem_details
+from .tools.get_practice import get_practice_plan
+from .tools.get_random_problem import get_random_problem_suggestion
+from .tools.get_upsolve import get_upsolve_suggestions
+from .tools.get_status import get_user_submission_status
+
+# Initialize the MCP Server
+mcp = FastMCP("cpmcp-oren")
+
+# ==========================================
+# TOOL 1: Get Single User Profile
+# ==========================================
+@mcp.tool()
+async def get_user(username: str) -> str:
+    """
+    Fetches a complete Codeforces profile in one call, returning:
+    - Current rating, max rating, title, and max title.
+    - Number of total contests given.
+    - Recent 5 contest rating changes (delta).
+    - Total distinct problems solved.
+    - Breakdown of solved problems by difficulty.
+    - Top 10 problem categories solved.
+    """
+    data = await fetch_and_parse_user_data(username)
+
+    if data["status"] == "error":
+        return f"❌ Error fetching user: {data['message']}"
+
+    output = f"**🧑‍💻 User Profile: {username}**\n\n"
+    
+    output += f"**🏆 Ratings & Titles:**\n"
+    output += f"- Current Rating: **{data['rating']}**\n"
+    output += f"- Max Rating: **{data['max_rating']}**\n"
+    output += f"- Current Title: {data['title']}\n"
+    output += f"- Max Title: {data['max_title']}\n\n"
+
+    output += f"**🏁 Contest History:**\n"
+    output += f"- Total Rated Contests Given: **{data['total_contests']}**\n"
+    
+    if data['recent_5']:
+        output += "- **Last 5 Rating Changes:**\n"
+        for c in data['recent_5']:
+            sign = "+" if c['newRating'] > c['oldRating'] else ""
+            output += f"  - {c['contestName']}: Rank {c['rank']} ({sign}{c['newRating'] - c['oldRating']}, {c['oldRating']} ➜ {c['newRating']})\n"
+    else:
+        output += "- No rated contests found.\n"
+    output += "\n"
+
+    output += f"**✅ Problem Solving Stats:**\n"
+    output += f"- Total Distinct Problems Solved: **{data['total_solved']}**\n"
+
+    if data['difficulty_stats']:
+        output += "- **Solved by Difficulty:**\n"
+        sorted_diff = sorted(data['difficulty_stats'].items(), key=lambda x: int(x[0]) if x[0] != 'Unrated' else 0)
+        for diff, count in sorted_diff:
+            output += f"  - Rating {diff}: {count} problems\n"
+    else:
+        output += "- No solved problems found by difficulty.\n"
+
+    if data['top_10_categories']:
+        output += "- **Top 10 Categories:**\n"
+        for tag, count in data['top_10_categories']:
+            output += f"  - {tag}: {count} problems\n"
+    else:
+        output += "- No categories found.\n"
+
+    return output
+
+# ==========================================
+# TOOL 2: Compare Two Users
+# ==========================================
+@mcp.tool()
+async def compare_user(user_a: str, user_b: str) -> str:
+    """
+    Compare two Codeforces users side-by-side. 
+    Returns a detailed comparison of ratings, titles, contest count, 
+    and problem solving breakdown (difficulty & category).
+    """
+    return await compare_users_data(user_a, user_b)
+
+# ==========================================
+# TOOL 3: Search Problem List
+# ==========================================
+@mcp.tool()
+async def get_problemlist(
+    min_rating: int = None,
+    max_rating: int = None,
+    topics: list = None,
+    sort_by: str = "recent",
+    match_type: str = "OR"
+) -> str:
+    """
+    Search the entire Codeforces problemset and return up to 10 problems.
+    
+    Parameters:
+    - min_rating: Minimum difficulty rating (e.g., 800)
+    - max_rating: Maximum difficulty rating (e.g., 2400)
+    - topics: List of tags to filter by (e.g., ["dp", "greedy"])
+    - sort_by: "recent" (newest first) or "oldest" (oldest first)
+    - match_type: "OR" (match any topic) or "AND" (must match ALL topics)
+    
+    Returns 10 problems with names, ratings, tags, and direct links.
+    """
+    try:
+        problems = await get_filtered_problems(
+            min_rating=min_rating,
+            max_rating=max_rating,
+            topics=topics,
+            sort_by=sort_by,
+            match_type=match_type
+        )
+        
+        if not problems:
+            return "No problems found matching your criteria. Try broadening your filters."
+
+        output = f"**💻 Found {len(problems)} Problems:**\n\n"
+        
+        for p in problems:
+            name = p.get('name', 'Unknown Problem')
+            contest_id = p['contestId']
+            index = p['index']
+            rating = p.get('rating', 'Unrated')
+            tags = ", ".join(p.get('tags', [])[:5])
+            url = f"https://codeforces.com/problemset/problem/{contest_id}/{index}"
+            
+            output += f"### [{name}]({url})\n"
+            output += f"- **Rating**: {rating}\n"
+            output += f"- **Tags**: {tags}\n\n"
+            
+        return output
+        
+    except Exception as e:
+        return f"❌ Error fetching problem list: {str(e)}"
+
+# ==========================================
+# TOOL 4: Get Full Problem Statement
+# ==========================================
+@mcp.tool()
+async def get_problem(contest_id: int, index: str) -> str:
+    """
+    Fetch the full problem statement, rating, and topics for a specific Codeforces problem.
+    Provide the contest ID and the problem index (e.g., contest_id=4, index='A').
+    """
+    try:
+        data = await get_problem_details(contest_id, index)
+        
+        if "error" in data:
+            return f"❌ {data['error']}"
+        
+        output = f"# {data['title']}\n\n"
+        output += f"**Link:** [View on Codeforces]({data['url']})\n\n"
+        
+        # The dropdown you requested!
+        output += f"📊 **Rating:** `{data['rating']}`  |  **Topics:** `{', '.join(data['topics'])}`\n\n"
+        output += f"---\n\n"
+           
+        output += "**Problem Statement:**\n\n"
+        output += data['statement']
+        
+        return output
+    except Exception as e:
+        return f"❌ Error fetching problem: {str(e)}"
+
+# ==========================================
+# TOOL 5: Get Practice Problems
+# ==========================================
+@mcp.tool()
+async def get_practiceproblems(username: str) -> str:
+    """
+    Analyzes a user's solved problems to identify their weakest topics.
+    Recommends up to 3 practice problems within +300 rating of their current level.
+    """
+    result = await get_practice_plan(username)
+    
+    if result["status"] == "error":
+        return f"❌ Error generating practice plan: {result['message']}"
+
+    output = f"**🎯 Practice Plan for `{username}`**\n\n"
+    output += f"Current Rating: **{result['rating']}**\n"
+    output += f"Identified Weak Topic(s): **{', '.join(result['weak_topics'])}**\n"
+    output += f"Target Rating Range: **{result['rating']} - {result['rating'] + 300}**\n\n"
+
+    if not result["problems"]:
+        output += "No suitable practice problems found in the target rating range. Try increasing your range or broadening topics."
+        return output
+
+    output += "**💻 Recommended Problems to Practice:**\n"
+    for idx, p in enumerate(result["problems"], 1):
+        name = p.get('name', 'Unknown Problem')
+        contest_id = p['contestId']
+        index = p['index']
+        rating = p.get('rating', 'Unrated')
+        tags = ", ".join(p.get('tags', [])[:5])
+        url = f"https://codeforces.com/problemset/problem/{contest_id}/{index}"
+        
+        output += f"\n**{idx}. [{name}]({url})**\n"
+        output += f"   - Rating: {rating}\n"
+        output += f"   - Topics: {tags}\n"
+        
+    return output
+
+# ==========================================
+# TOOL 7: Get Random Practice Problem
+# ==========================================
+@mcp.tool()
+async def get_random_practice(username: str) -> str:
+    """
+    Ignore weaknesses and recommend a single, completely random Codeforces problem 
+    within +/- 300 rating of the user's current rating. 
+    Great for a fresh, challenging surprise!
+    """
+    result = await get_random_problem_suggestion(username)
+    
+    if "error" in result:
+        return f"❌ Error generating random problem: {result['error']}"
+
+    p = result
+    name = p.get('name', 'Unknown Problem')
+    contest_id = p['contestId']
+    index = p['index']
+    rating = p.get('rating', 'Unrated')
+    tags = ", ".join(p.get('tags', [])[:5])
+    url = f"https://codeforces.com/problemset/problem/{contest_id}/{index}"
+    
+    output = f"**🎲 Random Practice Problem for `{username}`**\n\n"
+    output += f"**[{name}]({url})**\n"
+    output += f"- **Rating**: {rating}\n"
+    output += f"- **Tags**: {tags}\n"
+    output += f"- *(Generated from range: Current Rating ± 300)*\n"
+    
+    return output
+
+# ==========================================
+# TOOL 8: Get Upsolve Problems
+# ==========================================
+@mcp.tool()
+async def get_upsolve(username: str) -> str:
+    """
+    Analyze the user's last 10 rated Codeforces contests.
+    Recommends up to 2 unsolved problems per contest if:
+    - The problem is unrated, OR
+    - The problem is rated within +/- 300 of the user's current rating.
+    This is perfect for targeted practice to improve rank!
+    """
+    result = await get_upsolve_suggestions(username)
+    
+    if result["status"] == "error":
+        return f"❌ Error generating upsolve list: {result['message']}"
+
+    if not result["suggestions"]:
+        return f"🎉 No upsolve problems found for `{username}` within +/- 300 of {result['rating']} rating. Either you solved them all, or they are out of your range!"
+
+    output = f"**📝 Upsolve Plan for `{username}`**\n"
+    output += f"(Based on last 10 rated contests. Current Rating: **{result['rating']}**)\n\n"
+
+    for item in result["suggestions"]:
+        p = item["problem"]
+        name = p.get('name', 'Unknown')
+        contest_id = p['contestId']
+        index = p['index']
+        rating = p.get('rating', 'Unrated')
+        tags = ", ".join(p.get('tags', [])[:3]) # Show top 3 tags
+        url = f"https://codeforces.com/problemset/problem/{contest_id}/{index}"
+        
+        output += f"### [{name}]({url})\n"
+        output += f"- **Contest:** {item['contest_name']}\n"
+        output += f"- **Rating:** {rating}\n"
+        output += f"- **Tags:** {tags}\n"
+        output += f"- **Why upsolve?** *{item['reason']}*\n\n"
+
+    return output
+
+# ==========================================
+# TOOL 10: Get User Submission Status
+# ==========================================
+@mcp.tool()
+async def get_status(username: str) -> str:
+    """
+    Fetch the last 1000 submissions of a user. Provides a summary of their 
+    AC/WA/TLE count, and details of their 20 most recent submissions.
+    Great for debugging how a user is performing on their current attempts.
+    """
+    result = await get_user_submission_status(username)
+    
+    if result["status"] == "error":
+        return f"❌ Error fetching submissions: {result['message']}"
+
+    output = f"**📊 Submission Status for `{username}`**\n\n"
+    output += result["summary"] + "\n"
+    
+    output += "**🕒 Most Recent 20 Submissions:**\n"
+    for sub in result["recent_submissions"]:
+        output += f"- **[`{sub['prob_name']}`]({sub['url']})**\n"
+        output += f"  - Verdict: {sub['verdict']}\n"
+        output += f"  - Time: {sub['time']} | Memory: {sub['memory']}\n"
+
+    return output

cf_mcp_orange-1.0.1/src/cpmcp_oren/__main__.py

@@ -0,0 +1,4 @@
+from . import mcp
+
+if __name__ == "__main__":
+    mcp.run(transport="stdio")