Skip to main content
Glama

Oi

by io.github.carhaix
OverviewDiscussionsAdmin

Server Details

Access Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.

Ownership verified

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.

Status
Unhealthy
Uptime
2.1% over 37 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
Repository
carhaix/oi-mcp
GitHub Stars
1

TDQS

A3.5/5.0

Scored across 38 tools

Disambiguation4/5

Resource prefixes (contexts, skills, guardrails, workflows, connections) make most tools clearly distinct, and parallel lifecycle verbs are scoped by resource name. The main ambiguity is within the guardrails publish/release/unpublish lifecycle and between brain.save-feedback, contexts.save-draft-feedback, and the two report tools, though detailed descriptions mostly resolve it.

Naming Consistency4/5

Tools overwhelmingly follow an oi.<resource>.<verb> snake_case pattern, with create/get/list/update/use repeated consistently across resource types. Deviations include resource-less oi.recommend, noun-style oi.auth.whoami, and inconsistent release handling (separate guardrails.release vs action=release on contexts/skills update).

Tool Count2/5

38 tools is too many for a single server, mainly because the same lifecycle pattern is repeated across Contexts, Skills, Guardrails, and Workflows. Each tool may be individually justifiable, but the set feels bloated and could benefit from consolidation or splitting into per-resource servers.

Completeness3/5

CRUD coverage is uneven: Guardrails have create/update/delete/list/get plus publish/unpublish/release, while Contexts, Skills, and Workflows lack any delete or archive tool, and Brain has only save-feedback with no read/update/delete path. Connections and auth are read/use-only, which may be intentional but leaves management actions absent.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 38 tool updates
    • First observedoi.auth.whoami
    • First observedoi.brain.save-feedback
    • First observedoi.connections.get
    • First observedoi.connections.list
    • First observedoi.connections.use
    • First observedoi.contexts.create
    • First observedoi.contexts.get
    • First observedoi.contexts.list
    • First observedoi.contexts.save-draft-feedback
    • First observedoi.contexts.search
    • First observedoi.contexts.start-session
    • First observedoi.contexts.update
    • First observedoi.contexts.use
    • First observedoi.effectiveness.report
    • First observedoi.guardrails.confirm
    • First observedoi.guardrails.create
    • First observedoi.guardrails.delete
    • First observedoi.guardrails.get
    • First observedoi.guardrails.list
    • First observedoi.guardrails.publish
    • First observedoi.guardrails.release
    • First observedoi.guardrails.unpublish
    • First observedoi.guardrails.update
    • First observedoi.recommend
    • First observedoi.skills.create
    • First observedoi.skills.get
    • First observedoi.skills.list
    • First observedoi.skills.publish
    • First observedoi.skills.search
    • First observedoi.skills.update
    • First observedoi.skills.use
    • First observedoi.usage.report
    • First observedoi.workflows.create
    • First observedoi.workflows.get
    • First observedoi.workflows.list
    • First observedoi.workflows.start-session
    • First observedoi.workflows.update
    • First observedoi.workflows.use

Related MCP Connectors

Related MCP Servers

  • fes-mcp

    hnegi01
    A
    license
    A
    quality
    A
    maintenance
    Enables AI clients to perform Sisense environment operations such as governance, asset and user/group management, lifecycle tasks, and health checks using the calling user's own credentials.
    36
    MIT
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.

Resources