
Cc25a Openai Api Agent Project123123123
ai.smitheryPublished by smithery.aiOfficial publisherv1.14.0Updated Oct 24, 2026
Look up the latest stock prices by ticker symbol across global markets. Get current price and esse…
The publisher's own server: 222wcnm Bilistalkermcp
Overview
A Smithery-hosted remote MCP server, built from an OpenAI API agent course project, that reportedly looks up stock prices by ticker across global markets.
- What you can do
- Look up the latest stock prices by ticker symbol across global markets, per the registry description, which is cut off after the current-price detail. The README describes the underlying project rather than the hosted tools: an OpenAI API agent app with function-calling tools defined in a tools.py file, also exposed as MCP tools. The project also covers uploading fine-tuning data (SFT, DPO, RFT) to OpenAI and configuring prompt IDs and response overrides. No tool list is published in the manifest, so the exact tool set is unconfirmed.
- When to use it
- When an assistant needs quick stock price lookups by ticker and you are comfortable connecting to a third-party hosted endpoint. Not a good fit if you need a documented, stable tool list or a self-hosted server.
- Requirements
- A remote streamable HTTP endpoint at server.smithery.ai. A bearer token is required in the Authorization header for Smithery authentication. The underlying project uses an OpenAI API key, a prompt ID and an optional password, but these are not declared in the manifest.
Installation
In SourceWeft
- Open Cc25a Openai Api Agent Project123123123 in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/ai.smithery%2Fcc25a-openai-api-agent-project123123123/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"cc25a-openai-api-agent-project123123123": {
"type": "http",
"url": "https://server.smithery.ai/@cc25a/openai-api-agent-project123123123/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
OpenAI API Agent School - Project
본 자료는 (주)에이아이캐슬에서 만든 OpenAI API로 배우는 Agent 개발 첫걸음 (OpenAI API Agent School) 강의 프로젝트 자료입니다.
[0] Install & Build (uv)
[1] 프로젝트 세팅
1.1. 환경 변수 (.env)
- .env 파일로 설정하거나 배포 환경에서 지정
OPENAI_API_KEY: Agent 앱 또는 파인튜닝할 데이터를 업로드할 때 사용할 OpenAI API 키PROMPT_IDAgent 앱에서 사용할 OpenAI 프롬프트 IDTITLE: Agent앱의 상단 제목PASSWORD: 비밀번호 설정 (비워둘 경우 누구나 접근 가능)- Agent 앱에서는 로그인해야 접근 가능해짐
- MCP 서버에서는
?password=<your-password>와 같이 쿼리스트링으로 전달해야 접근 가능
1.2. config.overrides.jsonc
- Agent 앱에서 openai api 요청시 responses create 에서 덮어 쓸 구성 값
- config.overrides.jsonc 파일로 설정하거나 배포 환경에서 지정
- 파일 위치
- 프로젝트 폴더 (우선 순위)
- /etc/secrets/
1.3. tools.py
- Agent 앱에서 Function Calling으로 사용할 함수.
- 또는 MCP 서버에서 tool로 사용할 함수.
- 파일 위치: tools.py
[2] 앱 실행
실행
-
포트: 환경변수
PORT값이 지정된 경우 이 값을 사용하며, 그렇지 않을 경우8000을 사용함. -
agent 앱 주소: https://localhost:8000/agent
-
mcp 서버 주소: https://localhost:8000/mcp
KEEPALIVE_URL
- 실행 중인 앱이 일정시간 동안 접속이 없으면 유휴상태가 될 경우
KEEPALIVE_URL를 github actions의 환경변수(secrets)에 지정하여 주기적으로 접속하는 cron 작업을 수행할 수 있음. - Fork한 경우 Fork한 레포지토리 접속하여 상단의 Actions 탭에서 Actions를 활성화 하고 .github/workflows/keepalive-url.yml 을 활성화 하세요.
- 레포지토리 > settings > Secrets and Variables > Actions > New repository secret 에 접속하여 아래와 같이 입력 (Secret에는 본인이 배포한 URL로 입력)
- 예시
- Name:
KEEPALIVE_URL - Secret:
https://<your-project-name>.onrender.com
- Name:
[3] 파인 튜닝 데이터
.env파일에 OPENAI_API_KEY를 등록해야 정상적으로 업로드 가능
3.1. SFT (Supervised Fine-tuning)
- 폴더 위치:
fine_tuning_data/supervised/ - 데이터 생성 및 업로드
3.2. DPO (Direct Preference Optimization)
- 폴더 위치:
fine_tuning_data/preference/ - 데이터 생성 및 업로드
3.3. RFT (Reinforcement Fine-tuning)
- 폴더 위치:
fine_tuning_data/reinforcement/ - 데이터 생성 및 업로드
Source: README.md at commit 2918021
Tools
0Version history
1- v1.14.0LatestSep 16, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Smithery integrations

222wcnm Bilistalkermcp
ai.smitheryOfficial publisher
Bilibili creator analysis server that lets an assistant look up a specific user's profile, videos, dynamics, articles, subtitles, followings and comments.

Zwldarren Akshare One Mcp
ai.smitheryOfficial publisher
Remote MCP server that gives an assistant read-only access to Chinese stock market data: historical and real-time prices, news, and financial statements.

Zhaoganghao Hellomcp
ai.smitheryOfficial publisher
A small remote MCP server that lets an assistant greet people by name and share background on the origin of 'Hello, World'.

Zeta Chain Cli
ai.smitheryOfficial publisher
A remote MCP server that lets an assistant generate friendly, customizable greetings for any name or audience.

Yuna0x0 Hackmd Mcp
ai.smitheryOfficial publisher
An MCP server that connects an assistant to the HackMD API so it can read, create, update and delete HackMD notes and manage teams.