Can I execute Apex code?

Yes — execute anonymous Apex. Returns compilation status, success/failure, and any exception details.

What metadata can I search?

ApexClass, ApexTrigger, CustomField, ValidationRule, Flow, and more via the Tooling API SOQL.

How do org limits work?

Shows remaining vs max for API calls, storage, daily queries, email limits, and more. Flags items below 10%.

Salesforce Admin & Metadata MCP Server for CrewAI 8 tools — connect in under 2 minutes

Name: Salesforce Admin & Metadata
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 8 Tools Framework

Connect your CrewAI agents to Salesforce Admin & Metadata through the Vinkius — pass the Edge URL in the `mcps` parameter and every Salesforce Admin & Metadata tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Salesforce Admin & Metadata Specialist",
    goal="Help users interact with Salesforce Admin & Metadata effectively",
    backstory=(
        "You are an expert at leveraging Salesforce Admin & Metadata tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Salesforce Admin & Metadata "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 8 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Salesforce Admin & Metadata MCP Server

The Salesforce Admin toolkit for AI agents.

When paired with CrewAI, Salesforce Admin & Metadata becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Salesforce Admin & Metadata tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Users — List and search active users with profiles and roles
Objects — List all objects, describe schemas with field details
Limits — Monitor API calls, storage, and rate limits
Metadata — Search Apex classes, triggers, flows via Tooling API
Apex — Execute anonymous Apex code
Profiles — List security profiles

The Salesforce Admin & Metadata MCP Server exposes 8 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Salesforce Admin & Metadata to CrewAI via MCP

Follow these steps to integrate the Salesforce Admin & Metadata MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 8 tools from Salesforce Admin & Metadata

Why Use CrewAI with the Salesforce Admin & Metadata MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Salesforce Admin & Metadata through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Salesforce Admin & Metadata + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Salesforce Admin & Metadata MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Salesforce Admin & Metadata for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Salesforce Admin & Metadata, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Salesforce Admin & Metadata tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Salesforce Admin & Metadata against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Salesforce Admin & Metadata MCP Tools for CrewAI (8)

These 8 tools become available when you connect Salesforce Admin & Metadata to CrewAI via MCP:

sf_describe_object

Returns every field with: API name, label, data type (string/number/date/reference/picklist/boolean), whether required or nullable, max length, reference target objects (for lookups), and picklist values (for picklist fields). Essential for understanding the data model before creating or querying records. Use when the user asks "what fields does Account have?" or needs to know valid picklist values. Describe the full schema of a Salesforce object — all fields, data types, relationships, picklist values, and validation rules

sf_execute_apex

Returns compilation success/failure, execution result, and debug logs. Use for admin tasks (data cleanup, batch operations), testing hypotheses, or running one-off scripts. CAUTION: this executes real code on the org — can modify data. Example: System.debug('Hello World'); Execute anonymous Apex code on the Salesforce org for admin tasks, data fixes, testing, or one-off operations

sf_list_objects

Returns all objects with their API name, label, whether they are queryable, createable, and custom. Includes standard objects (Account, Contact, Lead, Opportunity, Case), custom objects (ending in __c), and managed package objects. Essential for data model discovery: "what objects are available?", "do we have a custom invoices object?" List all queryable and createable objects in the Salesforce org — standard, custom, and managed package objects

sf_list_profiles

Returns profile name, description, user type, and license type. Profiles control what users can see and do in Salesforce — they define object permissions, field-level security, and page layouts. Use when the user asks about permissions, needs to audit access levels, or wants to understand the security model. List Salesforce profiles (permission sets) with name, description, and user type for access control auditing

sf_list_users

Returns user name, email, profile name, role name, user type (Standard/Chatter/etc.), and last login date. Use when the user asks about team members, needs user IDs for record assignment, wants to audit active accounts, or check last login dates for license management. List active Salesforce users with their profile, role, email, user type, and last login date for team management

sf_org_limits

Returns current usage vs. maximum for: daily API calls, data storage, file storage, SOQL queries, DML operations, email invocations, and more. Flags any limits below 10% remaining. Use for capacity monitoring, API governance, or when the user asks about org health and limit consumption. Get API and storage usage limits for the Salesforce org — current consumption vs. maximum for API calls, storage, and more

sf_search_metadata

Supported objects: ApexClass, ApexTrigger, CustomField, ValidationRule, Flow, FlowDefinition, CustomObject, etc. Example: SELECT Id, Name, Body FROM ApexClass WHERE Name LIKE '%Account%'. Use when the user asks about code, automations, custom fields, or configuration metadata in the org. Search Salesforce metadata via the Tooling API — find Apex classes, triggers, custom fields, validation rules, flows, and more

sf_search_users

Returns user name, email, username, profile, role, and login info. Use to find a specific person in the org, look up who owns a record, or get user IDs for API operations. Search Salesforce users by name, email, or username to find specific team members or administrators

Example Prompts for Salesforce Admin & Metadata in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Salesforce Admin & Metadata immediately.

"Describe the Opportunity object schema"

"Check our API limits"

"List all Apex classes containing Account"

Troubleshooting Salesforce Admin & Metadata MCP Server with CrewAI

Common issues when connecting Salesforce Admin & Metadata to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Salesforce Admin & Metadata + CrewAI FAQ

Common questions about integrating Salesforce Admin & Metadata MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.