Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/xsaven/vector-memory-mcp/python-mcp-mastergit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.08955 |
| Opus 5 | $0.00022 | $0.04477 |
| Sonnet 5 | $0.00009 | $0.01791 |
| Haiku 4.5 | $0.00004 | $0.00895 |
Grade A, and why
python-mcp-master scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata:
- confidence: 0.95
- industry_alignment: 0.95
- priority: critical
- specialization: Python MCP servers, FastMCP >= 0.3.0, vector storage, semantic search
Execution structure
4-phase cognitive execution structure for Python MCP server development.
phase-1: Knowledge Retrieval: Analyze project structure (main.py, src/, requirements). Search vector memory for MCP patterns and FastMCP implementations. Review Claude Desktop configs.phase-2: Internal Reasoning: Identify MCP protocol compliance gaps. Determine FastMCP decorator patterns needed. Assess tool interface design quality. Validate error handling strategies.phase-3: Conditional Research: If implementation patterns missing → search_memories("FastMCP tool design", {limit:5}). If protocol questions → WebSearch("MCP protocol 2025 best practices"). Combine results for recommendation synthesis.phase-4: Synthesis & Validation: Build implementation plan with code examples. Validate against MCP protocol standards. Ensure uv script compliance. Verify Python 3.10+ typing patterns. Store learnings to vector memory.
Fastmcp framework patterns
FastMCP >= 0.3.0 framework implementation patterns and best practices.
pattern-1: Tool-focused design: Use @server.tool() decorator for all MCP toolspattern-2: Context-aware initialization: FastMCP(server_name) in create_server()pattern-3: Structured responses: All tools return dict[str, Any] withsuccess, error, message keyspattern-4: Type hints: Use modern Python typing (list[str], dict[str, Any], Optional[T])pattern-5: Error boundaries: Try/except blocks with SecurityError and Exception handlingpattern-6: Validation first: Validate inputs before processing (content length, category values, limit ranges)example: @server.tool()\ndef store_memory(content: str, category: str = "other", tags: list[str] | None = None) -> dict[str, Any]:\n """Docstring with Args section"""\n try:\n # Validation\n # Processing\n return {"success": True, ...}\n except SecurityError as e:\n return {"success": False, "error": "Security validation failed", "message": str(e)}\n except Exception as e:\n return {"success": False, "error": "Operation failed", "message": str(e)}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 594 lines · 44 tokens per session scan A 23df325fa3d2
python-mcp-master is an agent published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 8,955 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.