Install
$ agentstack add skill-manojbajaj95-mcp-skill-buffer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
buffer
Use this skill when you need to work with buffer through its generated async Python app, call its MCP-backed functions from code, or inspect available functions with the mcp-skill CLI.
Authentication
This MCP server uses Bearer token authentication. The API key is persisted to ~/.mcp-skill/auth/ after first use, so subsequent runs can omit it.
# First use — provide and persist the key
app = BufferApp(auth="YOUR_API_KEY")
# Subsequent uses — loaded from disk automatically
app = BufferApp()
The key is sent as Authorization: Bearer on every request.
Dependencies
This skill requires the following Python packages:
mcp-skill
Install with uv:
uv pip install mcp-skill
Or with pip:
pip install mcp-skill
Python Usage
Use the generated app directly in async Python code:
import asyncio
from buffer.app import BufferApp
async def main():
app = BufferApp(auth="YOUR_API_KEY")
result = await app.get_account()
print(result)
asyncio.run(main())
Async Usage Notes
- Every generated tool method is
async, so call it withawait. - Use these apps inside an async function, then run that function with
asyncio.run(...)if you are in a script. - If you forget
await, you will get a coroutine object instead of the actual tool result. - Be careful when mixing this with other event-loop environments such as notebooks, web servers, or async frameworks.
Discover Functions with the CLI
Use the CLI to find available apps, list functions on an app, and inspect a function before calling it:
uvx mcp-skill list-apps
uvx mcp-skill list-functions buffer
uvx mcp-skill inspect buffer get_account
Important: Add .agents/skills to your Python path so imports resolve correctly:
import sys
sys.path.insert(0, ".agents/skills")
from buffer.app import BufferApp
Or set the PYTHONPATH environment variable:
export PYTHONPATH=".agents/skills:$PYTHONPATH"
Preferred: use uv run (handles dependencies automatically):
PYTHONPATH=.agents/skills uv run --with mcp-skill python -c "
import asyncio
from buffer.app import BufferApp
async def main():
app = BufferApp(auth='YOUR_API_KEY')
result = await app.get_account()
print(result)
asyncio.run(main())
"
Alternative: use python directly (install dependencies first):
pip install mcp-skill
PYTHONPATH=.agents/skills python -c "
import asyncio
from buffer.app import BufferApp
async def main():
app = BufferApp(auth='YOUR_API_KEY')
result = await app.get_account()
print(result)
asyncio.run(main())
"
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: manojbajaj95
- Source: manojbajaj95/mcp-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.