Salesforce AI Agent MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | Port for SSE mode | 3000 |
| LOG_LEVEL | No | debug | info | warn | error | info |
| JIRA_EMAIL | Yes | Your Atlassian account email | |
| N8N_API_KEY | No | Generate at n8n Settings -> API -> Create API Key | |
| SF_PASSWORD | Yes | Your Salesforce password | |
| SF_USERNAME | Yes | Your Salesforce username | |
| N8N_BASE_URL | No | Your n8n instance URL | |
| SF_CLIENT_ID | Yes | Connected App Consumer Key | |
| SF_LOGIN_URL | Yes | https://login.salesforce.com (prod) or https://test.salesforce.com (sandbox) | |
| JIRA_BASE_URL | Yes | e.g. https://your-org.atlassian.net | |
| JIRA_API_TOKEN | Yes | Generate at Atlassian API Tokens | |
| SF_API_VERSION | No | API version, e.g. v61.0 | v61.0 |
| SF_CLIENT_SECRET | Yes | Connected App Consumer Secret | |
| SF_SECURITY_TOKEN | Yes | Reset at Setup -> Personal Information -> Reset Security Token |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jira_get_storyA | Fetch a Jira story by issue key. Returns summary, description, acceptance criteria, status, labels, assignee, and all custom fields. |
| jira_update_story_statusA | Transition a Jira story to a new status. The available transitions depend on the current workflow configuration. Common statuses: 'To Do', 'In Progress', 'In Review', 'Done', 'Blocked'. |
| jira_post_commentA | Post a comment to a Jira story. Used by the AI agent to document deployment results, ask for clarification, or provide status updates. Supports plain text with paragraphs separated by blank lines. |
| jira_search_storiesA | Search Jira stories using JQL (Jira Query Language). Returns matching issues with full details. Example JQL: 'label = "sf-config" AND status = "To Do" AND project = SFDC ORDER BY created DESC' |
| salesforce_get_object_fieldsA | Query all existing fields on a Salesforce object using the REST API describe endpoint. Returns field names, labels, types, lengths, and picklist values. |
| salesforce_create_custom_fieldB | Create a custom field on a Salesforce object using the Tooling API. Supports all standard field types including Text, Number, Picklist, Checkbox, Date, Lookup, and more. |
| salesforce_create_validation_ruleB | Create a validation rule on a Salesforce object using the Tooling API. The rule evaluates an error condition formula and displays an error message when the formula returns true. |
| salesforce_deploy_metadataB | Trigger a Salesforce metadata deployment using the Metadata API. The metadata must be provided as a base64-encoded ZIP file containing a standard Salesforce metadata package. |
| salesforce_get_deployment_statusA | Poll the status of a Salesforce metadata deployment by its deployment ID. Returns component counts, errors, and test results. |
| salesforce_queryA | Execute a SOQL query against Salesforce and return the results. Use this to verify field values after deployment, check existing records, or validate configuration. |
| n8n_trigger_workflowA | Trigger a specific n8n workflow by its webhook URL, passing a JSON payload. This enables Claude to kick off the full Salesforce automation pipeline — for example, by sending a Jira issue key to start the analysis and deployment workflow. |
| n8n_get_execution_statusA | Retrieve the current status and output data of an n8n workflow execution by its execution ID. Use this to poll whether a triggered workflow has completed successfully. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct action on a specific resource: Jira stories, Salesforce metadata/objects, and n8n workflows. There is no overlap between tools like get_deployment_status and get_execution_status because they operate on different systems.
All tool names follow a consistent pattern of domain_verb_noun (e.g., jira_get_story, salesforce_create_custom_field, n8n_trigger_workflow). Even salesforce_query fits, as 'query' functions as both verb and noun without breaking the convention.
The 12 tools are well-scoped for a cross-platform integration server covering Jira, Salesforce, and n8n. Each tool serves a clear purpose with no redundancy, so the count feels appropriate for the domain.
The tool surface covers the core workflow: fetching Jira stories, searching, commenting, modifying Salesforce metadata, deploying, and triggering/polling n8n workflows. Minor gaps exist, such as no update/delete for validation rules or custom fields, but the main lifecycle is adequately covered.