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 commands/sideshiftapp/sideshift-mcp-server/sideshift-connectgit clone --depth 1 https://github.com/SideShiftApp/sideshift-mcp-serverWrote 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/commands/sideshiftapp/sideshift-mcp-server/sideshift-connect)<a href="https://agentmods.dev/commands/sideshiftapp/sideshift-mcp-server/sideshift-connect"><img src="https://agentmods.dev/badge/commands/sideshiftapp/sideshift-mcp-server/sideshift-connect.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00295 |
| Opus 5 | $0.00015 | $0.00148 |
| Sonnet 5 | $0.00006 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
sideshift-connect 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 today.
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.
What it actually says
Connect SideShift
- Check whether the
sideshiftMCP server and itswhoamitool are available. - If they are available, call
whoami. The first call may open SideShift's OAuth consent flow in the user's browser or host connection UI. - Ask the user to complete sign-in, choose the intended company, review the requested scopes, and approve. Do not ask the user to paste any token or secret into chat.
- After authorization completes, call
whoamiagain. - Report:
- the exact connected company ID, and its name if returned by the server;
- whether the connection is sandboxed;
- the granted scopes relevant to the user's intended work;
- any missing scope or subaccount delegation, distinguishing team restrictions from consent.
- Continue already authorized work when the connected company matches the stated target. Ask for the target only if it is ambiguous or different. For agencies, follow the per-call delegation procedure in sideshift-setup.
If the SideShift MCP server is unavailable, ask the user to enable or reinstall the SideShift plugin in the current host and reload its plugins/connections, then retry whoami. Do not add a second manual MCP definition or create an API-key fallback.
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.
- today Changed a7469324bc42
- 5d ago First seen · 20 lines · 29 tokens per session scan A 14935efca897
sideshift-connect is a command published in the GitHub repository SideShiftApp/sideshift-mcp-server (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 295 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
scrape
Scrape public posts from X, LinkedIn or Hacker News in a signed-out local browser.
sap-table-dump
Read ALL rows from the table on the current SAP screen, handling pagination for both ALV grids and TableControls.
browse
You have access to a browser via the MCP Browser Bridge tools. Use them to interact with web pages.
model-audit
Audit model usage across the team to identify cost optimization opportunities.
usage-report
Generate a comprehensive team usage and spending report for the current billing cycle.
spend-check
Quick check on current team spending with alerts for any concerning patterns.