Governed AI agents for the software your company already runs. 400+ connectors behind one org-wide endpoint, where every call resolves against the current role of the person the agent acts for, not against the connection. Works with Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 52 tools
The resource-prefixed names make most tools easy to separate, and the descriptions are unusually explicit about boundaries. The main confusion risk is the cluster of tool-listing/execution surfaces: connection.list_tools, connector.list_tools, search_tools, toolbox.execute, and synthetic_tool.execute overlap enough to cause occasional misselection. Overall mostly distinct, with a few near-overlapping pairs.
The dominant pattern is clear and consistent: elaichi__<resource>__<verb> in snake_case. The two unprefixed tools, execute_tool and search_tools, break the pattern, and a few names like offboarding and set_roles deviate from strict verb phrasing. Still predictable and readable overall.
52 tools is well above the calibration threshold for 'too many' even for a broad administration platform. Each resource area has several CRUD-style operations, but the total feels heavy for a single MCP surface. The count will make tool selection and navigation burdensome.
Many lifecycle operations that the tool descriptions themselves reference are not exposed: deletions, unsharing, role create/update/delete, member delete, invite delete/resend, team remove_member/delete, and transfer operations. These missing operations create dead ends during common governance workflows. Core read/create/update paths exist, but the surface is significantly incomplete relative to its own described domain.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
elaichi__team__create1 field changedInput schema / properties / member_idsAdded value: +{
+ "description": "USER ids (`usr_…`) from member.list to add as ordinary members alongside you. Optional — omit for a team with only you on it. You are always added as administrator regardless of whether your own id appears here.",
+ "items": {
+ "type": "string"
+ },
+ "maxItems": 50,
+ "type": "array"
+}elaichi__access_request__createelaichi__access_request__getelaichi__access_request__listelaichi__access_request__resolveelaichi__access_request__withdrawelaichi__connection__createelaichi__connection__getelaichi__connection__listelaichi__connection__list_toolselaichi__connection__reconnectelaichi__connection__renameelaichi__connection__shareelaichi__connector__getelaichi__connector__listelaichi__connector__list_toolselaichi__feedback__createelaichi__invite__createelaichi__invite__listelaichi__member__getelaichi__member__listelaichi__member__offboardingelaichi__member__set_roleselaichi__organization__getelaichi__permission__listelaichi__role__getelaichi__role__listelaichi__synthetic_tool__createelaichi__synthetic_tool__executeelaichi__synthetic_tool__getelaichi__synthetic_tool__listelaichi__synthetic_tool__updateelaichi__team__add_memberelaichi__team__createelaichi__team__getelaichi__team__listelaichi__team__set_member_adminelaichi__team__updateelaichi__template__createelaichi__template__getelaichi__template__listelaichi__template__set_entrieselaichi__template__shareelaichi__template__updateelaichi__toolbox__createelaichi__toolbox__executeelaichi__toolbox__getelaichi__toolbox__listelaichi__toolbox__set_entrieselaichi__toolbox__shareelaichi__toolbox__updateexecute_toolsearch_tools
Add one secure layer between your agents and this server.