Borrowing it
Nothing to install: this file belongs to asgard-ai-platform/mcp-sf-express. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asgard-ai-platform/mcp-sf-express/main/CLAUDE.mdgit clone --depth 1 https://github.com/asgard-ai-platform/mcp-sf-expressWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/asgard-ai-platform/mcp-sf-express/claude-md)<a href="https://agentmods.dev/instructions/asgard-ai-platform/mcp-sf-express/claude-md"><img src="https://agentmods.dev/badge/instructions/asgard-ai-platform/mcp-sf-express/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/asgard-ai-platform/mcp-sf-express/claude-md"><img src="https://agentmods.dev/badge/instructions/asgard-ai-platform/mcp-sf-express/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00719 | $0.00719 |
| Opus 5.5 | $0.00288 | $0.00288 |
| Sonnet 5.5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
mcp-sf-express CLAUDE.md 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 2mo ago.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server — SF Express
Overview
MCP (Model Context Protocol) server exposing SF Express Open Platform tools over stdio (JSON-RPC 2.0). Integrations:
- OAuth2 access token (
grantType=password, form-encoded) std/servicebusiness gateway (form-encodedpartnerID,requestID,serviceCode,timestamp,msgData, andaccessTokenormsgDigest)
Part of the Asgard AI Platform ecosystem.
Setup
uv sync
cp .env.example .env
# Set SF_PARTNER_ID and SF_SECRET in .env
Run
uv run --env-file .env python mcp_server.py
# or
uv run --env-file .env mcp-sf-express
Test
# Live sandbox OAuth2 POST + parsed JSON (works with placeholder creds)
uv run python scripts/auth/test_connection.py
# Unit tests (mocked HTTP)
uv run pytest tests/ -q
# Registered tools smoke list
uv run python tests/test_all_tools.py
Architecture
stdio (JSON-RPC 2.0)
→ mcp_server.py (imports tools to register handlers)
→ app.py (FastMCP singleton: mcp-sf-express)
→ tools/sf_express_tools.py (@mcp.tool)
→ connectors/sf_express_client.py (HTTP: OAuth + std/service)
→ connectors/sf_std_service.py (request IDs, timestamps, msgDigest, form build, normalization)
→ config/settings.py (SF_ENV, URLs, timeouts)
Environment variables
| Variable | Purpose |
|---|---|
SF_ENV |
sandbox (default) or prod |
SF_PARTNER_ID |
OAuth partnerID and default std/service partner |
SF_SECRET |
OAuth secret (check word) and default digest input for std/service |
SF_HTTP_TIMEOUT_SECONDS |
Request timeout (default 30) |
SF_OAUTH_URL |
Optional override for token endpoint |
SF_STD_SERVICE_URL |
Optional override for std/service URL |
Conventions
- English for code, docstrings, and tool descriptions
- Tools return
dict(raw SF JSON plus_summary, and_requestmeta for std/service calls) - Use
connectors/sf_express_client.pyfor HTTP — do not callrequestsdirectly from tools - Pure request shaping lives in
connectors/sf_std_service.py
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.
- 2mo ago First seen · 81 lines · 719 tokens per session scan A c7e6b4663ee5
mcp-sf-express CLAUDE.md is an instructions file published in the GitHub repository asgard-ai-platform/mcp-sf-express (0 stars, last pushed 6mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0029 per session on Opus 5.5. 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 2026-08-31.
mcp-sf-express CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-sf-express CLAUDE.mdasgard-ai-platform/mcp-sf-express | Instructions file | 0 | 6mo ago | MIT | A | 719 | Claude Code |
| vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags | Instructions file | 25 | today | MIT | A | 553 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |