Mencoro

Set a member's project access

set_member_project_access

Destructive

Set which projects of the organization a member reaches: every project (mode "all") or only the projects in projectIds (mode "selected"); a project outside a selection answers as if it did not exist. It applies from the member's next request, including through their API keys and MCP connections. An owner always reaches every project and cannot be limited. memberId is the member id from list_members, not the user id; projectIds come from list_projects. Requires a confirmationToken: call preview_operation with tool "set_member_project_access" and these arguments first, show the returned plan to the user, and call this tool only after the user explicitly agrees. Needs the organization:manage permission and the owner role.

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": {
      "organizationId": "<organizationId>",
      "memberId": "<memberId>",
      "mode": "<mode>",
      "confirmationToken": "<confirmationToken>"
    },
    "name": "set_member_project_access"
  }
}

Input Schema

Name	Required	Description
`mode`	Yes
`memberId`	Yes
`requestId`	No	Optional idempotency key, 8-255 printable characters. Reuse it only to retry this same call.
`projectIds`	No	The projects a "selected" access reaches: at least one and at most 500 distinct projects, all of this organization; a repeated id counts once. Leave it out for "all".
`organizationId`	Yes
`confirmationToken`	Yes

Output Schema

Name	Required	Description
`id`	Yes
`role`	Yes
`state`	Yes
`userId`	Yes	The user this membership belongs to
`isActive`	Yes
`joinedAt`	Yes
`projectIds`	Yes	The projects a selected access reaches; empty when the mode is all
`projectAccessMode`	Yes	Which projects of the organization the member reaches: every project, or only projectIds

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the destructiveHint=true annotation: it discloses that changes take effect on the member's next request including through API keys and MCP connections, that owners are immune, and that out-of-selection projects behave as nonexistent. No contradiction with the destructive/mutation annotations.

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?

Dense but front-loaded, leading with the mode semantics before constraints and the confirmation workflow. A few clauses could be tightened (permission/role stated last), but nearly every sentence adds operative information.

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

Completeness5/5

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

For a destructive, non-idempotent mutation with an output schema and partial schema coverage, the description supplies the confirmation protocol, permission requirements, and cross-tool id sourcing an agent needs to call it safely and 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 only 33% schema coverage the description carries real weight: it disambiguates memberId (member id from list_members, not user id), sources projectIds from list_projects, and explains the mode/projectIds relationship plus the confirmationToken acquisition path. organizationId and requestId are not covered in prose (requestId is documented in-schema), which keeps it just short of full marks.

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+resource ('Set which projects ... a member reaches') and immediately distinguishes the two modes with exact enum values. An agent can tell this apart from change_member_role or set_tracked_query_passes without opening 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 says when each mode applies, what happens for a project outside a selection, and that an owner cannot be limited. It also names the required prerequisite flow (preview_operation, show plan, wait for explicit user agreement) and the necessary permission/role.

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

All Mencoro tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.