$ loading_
Query Salesforce data, analyze opportunities, and create cases via MCP.
This MCP tool is described as interacting with Salesforce data and services, which implies normal external-service access and code execution capabilities. The available material is sparse and the README is missing, but it is open source and shows no explicit malicious behavior or clear over-privilege red flags, so the overall posture is caution rather than high risk.
The material declares no keys or environment variables, but the tool's functionality involves access to Salesforce data and services, so the real authentication model is unclear and may rely on existing host session or platform identity. No explicit high-sensitivity secret requirement is shown, but the opaque auth model warrants caution about possible reuse of existing Salesforce privileges.
Although no remote endpoint is listed in the metadata, the description explicitly says it interacts with Salesforce data and services, which normally implies sending queries, case-creation requests, or agent-invocation payloads to Salesforce-related services. The actual egress destinations are not documented here, so the concrete domains and transmitted data scope should be verified.
The system flags that this tool executes code; this is a normal capability for an MCP tool and alone does not justify a high-risk rating. The material does not specify which local commands, subprocesses, or extra privileges are used, so it should be run in a constrained environment and its actual execution path should be inspected.
Based on the description, the tool can read Salesforce account and opportunity information, create cases, and invoke an AI agent, indicating access to business objects and some write capability. There is no stated need for local file read/write and no obvious system-level data access beyond its purpose, but its Salesforce object permissions should be checked for least privilege.
A positive factor is that there is an auditable open-source repository, which materially lowers black-box risk. However, it comes from a third-party registry, the repository has no declared license, zero stars, unknown maintenance status, and no README, so maturity and reviewability are limited; source code and dependencies should be reviewed before installation.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Salesforce-Hosted-Custom-Mcp-Server" yet — see the docs or source repo.
Use the Salesforce MCP tools to summarize a target account’s key metrics: recent activity, opportunity value, stage distribution, and risks, then give a brief conclusion.
An account overview with key metrics and risk highlights.
Query the highest-value opportunities from the last 30 days, organize them by stage and expected close date, and include the owner.
A ranked opportunity list with stage, close date, and owner.
Create a Salesforce case for the following issue and invoke the AI agent to generate resolution suggestions: the customer cannot log in, possibly due to a failed password reset.
The created case details plus AI-generated resolution suggestions.
Access Salesforce Tooling API via AI for metadata, queries, analysis, and debugging.
Connect Salesforce APIs for queries, record CRUD, metadata access, and GenAI workflows.
Connect an MCP AI assistant to Salesforce for data, schema, Apex, and deployments.
Let AI query, update, and analyze Salesforce CRM data without API glue code.
Use natural language to manage Salesforce data, schema, DevOps, and analytics.
Read and write Salesforce CRM objects for multi-tenant integrations and automation.