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 skills add advancedcommunities/salesforce-mcp-server --skill salesforcegit clone --depth 1 https://github.com/advancedcommunities/salesforce-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/skills/advancedcommunities/salesforce-mcp-server/salesforce)<a href="https://agentmods.dev/skills/advancedcommunities/salesforce-mcp-server/salesforce"><img src="https://agentmods.dev/badge/skills/advancedcommunities/salesforce-mcp-server/salesforce.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 | $0.00048 | $0.02682 |
| Opus 5 | $0.00024 | $0.01341 |
| Sonnet 5 | $0.00010 | $0.00536 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade A, and why
salesforce 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 8d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salesforce MCP Server — Skill Guide
Overview
The Salesforce MCP Server gives you 40 tools, 5 prompts, and 5 resources to interact with Salesforce orgs through the Salesforce CLI. This skill teaches you how to choose the right tool, chain tools into workflows, and avoid common mistakes.
Start Here: Establish Org Context
Before doing anything else, determine the target org and check permissions.
- Get the default org — call
get_default_org. If a default is set, you can omittargetOrgfrom all subsequent calls. - List connected orgs — call
list_connected_salesforce_orgsif the user hasn't specified which org to use. - Check permissions — call
get_server_permissionsto see if the server is in read-only mode and which orgs are allowed. - Set a default — if the user picks an org, call
set_default_orgso future calls don't needtargetOrg.
Rule: Never guess the org. Always resolve it first.
Tool Selection Guide
Querying Data
| Need | Tool | Why |
|---|---|---|
| Structured query on a single object with field conditions | query_records |
SOQL — precise field selection, WHERE clause, ORDER BY, LIMIT |
| Text search across multiple objects | search_records |
SOSL — FIND {term} IN ALL FIELDS RETURNING Obj1, Obj2 |
| Export large result sets to CSV/JSON | query_records_to_file |
Streams results to a file to avoid context window bloat |
- Use
query_recordsfor most data retrieval tasks (exact field filters, relationships, aggregations). - Use
search_recordsonly when you need cross-object keyword search (e.g., "find all records mentioning Acme Corp"). - Never build SOSL when a simple SOQL WHERE clause suffices.
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.
- 8d ago First seen · 242 lines · 48 tokens per session scan A 64f0dee76f58
salesforce is a skill published in the GitHub repository advancedcommunities/salesforce-mcp-server (31 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 2,682 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 2026-08-30.
Other skills, from other repositories
sfcc-localserviceregistry
Guide for creating server-to-server integrations in Salesforce B2C Commerce using LocalServiceRegistry. Use this when asked to integrate external APIs, create HTTP services, implement OAuth flows, or configure service credentials.
sfcc-ocapi-hooks
Guide for implementing OCAPI hooks in Salesforce B2C Commerce. Use this when asked to create OCAPI hooks, extend API endpoints, validate API requests, or modify API responses.
sfcc-scapi-hooks
Guide for implementing SCAPI hooks in Salesforce B2C Commerce. Use this when asked to create SCAPI hooks, extend Shopper API endpoints, validate API requests, or modify API responses for headless commerce.
sfcc-cartridge-development
Guide for creating, configuring, and deploying custom SFRA cartridges in Salesforce B2C Commerce. Use this when asked to create a new cartridge, set up a cartridge structure, or work with cartridge paths.
sfcc-job-development
Guide for developing custom jobs in Salesforce B2C Commerce Job Framework. Use this when asked to create batch jobs, scheduled tasks, chunk-oriented processing, or task-oriented jobs.
sfcc-script-evaluation
Guide for using the evaluatescript tool to execute JavaScript on SFCC instances via the script debugger.