Skip to main content
Glama

FMEPM Connect for Oracle EPM

Change Oracle security

change_oracle_security
Destructive

Adds, removes and updates Oracle users, groups, user memberships and granular roles. Batch changes have one preview. A membership batch uses an existing group CSV. User role updates choose append or overwrite. Imports and exports access permissions. Admin profile and enabled Security changes are required. Each action needs a prior exact preview. Production needs a second approval naming the pod. New users use Oracle password reset; no password is accepted. Removal cannot restore identity ids, sessions or lost access. Permission import uses an existing pod CSV and preserves permissions outside the file. Use it after reading users and roles with read_oracle_directory and read_access_reports. https://docs.oracle.com/en/cloud/saas/enterprise-performance-management-common/prest/lcm_intro_provisioning.html For a write, I require a preview first, then confirm: true and its confirmationToken. The token lasts ten minutes and works once.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "change": "<change>"
    },
    "name": "change_oracle_security"
  }
}

Input Schema

NameRequiredDescriptionDefault
changeYesOne exact security action. Unknown fields and passwords are refused.
confirmNoSet true after the user has approved the previewed change
demoStageNoDemo production approval rehearsal. Real stage comes from the saved connection.test
connectionNoConnection id or label from list_connections. Defaults to the user's default connection.
applicationNoApplication name, resolved from the connection when omitted; pod-wide identity operations still affect the whole identity domain.
productionPodNoExact pod name from the second production preview.
confirmationTokenNoSingle-use token from this exact preview. Send it with confirm: true after the user approves. It expires after ten minutes.
productionApprovalIdNoReceipt returned only after approving the first production preview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the destructive/openWorld annotations: batch changes share one preview, membership batches consume an existing group CSV, role updates are append-or-overwrite, permission import preserves out-of-file permissions, and removal cannot restore identity ids or sessions. The confirmationToken lifetime and single-use constraint are spelled out, though the 10-minute expiry is repeated in the schema. Not a contradiction with destructiveHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the capability sentence, then the workflow and safety rules. The many short sentences are dense but each carries a distinct rule; the Oracle docs URL is the one piece that doesn't earn its place in an agent-facing description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-action union schema with no output schema, the description covers the critical friction points: preview-per-action, token semantics, production double approval, password policy, and irreversibility of removals. It doesn't mention the catalog_security or export_permissions actions, but the schema's action consts enumerate those, so an agent can still proceed correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds real meaning: confirm must be true only after user approval, confirmationToken is single-use and 10-minute, productionPod must be the exact pod name from the second preview, and role updates take append or overwrite. It leaves connection, application and demoStage mostly to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb set (adds, removes, updates) and precise resources (Oracle users, groups, memberships, granular roles), and names the read siblings (read_oracle_directory, read_access_reports) that precede it. An agent can distinguish this mutation tool from those readers without inspecting the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly sequences usage: read first with read_oracle_directory and read_access_reports, then act. It also states the preview-then-confirm protocol and that production requires a second approval naming the pod, plus the exclusion that no password is accepted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources