cf-mcp-orange
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_userA | Fetches a complete Codeforces profile in one call, returning:
|
| compare_userB | Compare two Codeforces users side-by-side. Returns a detailed comparison of ratings, titles, contest count, and problem solving breakdown (difficulty & category). |
| get_problemlistA | Search the entire Codeforces problemset and return up to 10 problems. Parameters:
Returns 10 problems with names, ratings, tags, and direct links. |
| get_problemA | 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'). |
| get_practiceproblemsA | Analyzes a user's solved problems to identify their weakest topics. Recommends up to 3 practice problems within +300 rating of their current level. |
| get_random_practiceA | 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! |
| get_upsolveB | Analyze the user's last 10 rated Codeforces contests. Recommends up to 2 unsolved problems per contest if:
|
| get_statusA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/spr7a/cf-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server