# sf_assign_skill_to_agent

Assigns a Skill to a Salesforce user (service agent) with a skill level rating. Creates a ServiceResource for the user if one does not already exist, then creates a ServiceResourceSkill record. skillName: the API name (DeveloperName) of the skill to assign username: the Salesforce username (e.g. agent@example.com) or user ID skillLevel: proficiency level from 0 to 10 (default 5) ServiceResource is the Field Service / OmniChannel representation of a user as a workable resource.

Agent View of the PolicyLayer registry record for `sf_assign_skill_to_agent`. HTML page: https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-assign-skill-to-agent

## Facts

- Tool: `sf_assign_skill_to_agent`
- Server: Salesforce Metadata Mcp (`salesforce-metadata-mcp`) — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp.md
- Install: `npx -y salesforce-metadata-mcp`
- Homepage: https://github.com/semwalajay83-sem/salesforce-metadata-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "sf_assign_skill_to_agent",
    "arguments": {}
  }
}
```

## Why sf_assign_skill_to_agent is rated Medium

This tool creates or modifies data by assigning skills to agents and potentially creating ServiceResource records. These are write operations that can be reversed (skills can be unassigned, records can be deleted). While it affects agent capability and workload allocation, it does not irreversibly delete data, execute code, or move money.

From the tool's own definition: "The tool 'Creates a ServiceResource for the user if one does not already exist, then creates a ServiceResourceSkill record.' This describes creating new records in Salesforce, which are reversible modifications."

## Use case

AI agents use sf_assign_skill_to_agent to create or update resources in Salesforce Metadata Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Salesforce Metadata Mcp environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Salesforce Metadata Mcp:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "sf_assign_skill_to_agent": {
      "limits": [
        {
          "counter": "sf_assign_skill_to_agent_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Salesforce Metadata Mcp (212)

- `sf_bulk_delete_records` — Destructive — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-bulk-delete-records.md
- `sf_delete_record` — Destructive — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-delete-record.md
- `sf_delete_scratch_org` — Destructive — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-delete-scratch-org.md
- `sf_activate_omniscript` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-activate-omniscript.md
- `sf_create_apex_class` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-apex-class.md
- `sf_create_apex_test_class` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-apex-test-class.md
- `sf_create_apex_trigger` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-apex-trigger.md
- `sf_create_flow` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-flow.md
- `sf_create_scheduled_job` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-scheduled-job.md
- `sf_create_scratch_org` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-scratch-org.md
- `sf_deactivate_flow` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-deactivate-flow.md
- `sf_deploy_metadata` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-deploy-metadata.md
- `sf_devops_promote_work_item` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-devops-promote-work-item.md
- `sf_execute_anonymous_apex` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-execute-anonymous-apex.md
- `sf_install_package` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-install-package.md
- `sf_promote_devops_work_item` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-promote-devops-work-item.md
- `sf_run_apex_tests` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-run-apex-tests.md
- `sf_send_email` — Execute — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-send-email.md
- `sf_check_code_coverage` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-check-code-coverage.md
- `sf_check_deploy_status` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-check-deploy-status.md
- `sf_check_devops_commit_status` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-check-devops-commit-status.md
- `sf_detect_devops_merge_conflict` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-detect-devops-merge-conflict.md
- `sf_explore_slds_blueprints` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-explore-slds-blueprints.md
- `sf_export_omnistudio_component` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-export-omnistudio-component.md
- `sf_export_records` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-export-records.md
- `sf_get_apex_test_results` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-apex-test-results.md
- `sf_get_dataraptor` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-dataraptor.md
- `sf_get_deployment_history` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-deployment-history.md
- `sf_get_event_logs` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-event-logs.md
- `sf_get_field_history` — Read — https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-field-history.md
- …and 182 more: https://policylayer.com/tools/io-github-semwalajay83-sem-salesforce-metadata-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-semwalajay83-sem-salesforce-metadata-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-semwalajay83-sem-salesforce-metadata-mcp