Is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server down?

mcp-registry/io.github.eno654/oxyo-mcp · registry v1.2.4 · server reports v1.2.0

Also listed as github/eno654/oxyo-mcp

One MCP connection for every live tool. Your agent finds the right tool and calls it through Glimind, and skips servers that are down. Free, no signup.Add to CursorVS CodeAdd to Claude Code copies a terminal command claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clients
healthy
Last checked 2026-11-22 17:22 UTC · handshake 330ms

As of 2026-11-22 17:22 UTC, the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 100% of Glimind's liveness checks.

uptime (30d checks)
100%
checks observed
290
outages (90d)
0
tools
19

Cuts coding agent token burn up to 72% continuously via contradiction-free memory & verification.

Point your MCP client at this streamable-http endpoint: https://oxyo.si/mcp

Agent-readiness: A (90/100)

A (90/100): 0 error(s), 2 warning(s) across 15 tool(s); ~5,593 tokens of tool definitions.
Scores higher than 60% of 27,661 MCP servers Glimind has audited.
Its tool list costs an agent ~5,593 tokens per session — more than 70% of servers.
93 → 90 since 2026-11-21
no tool-poisoning patterns
Descriptions100
Safety hints100
Schemas87
Protocol40
Stability92
Token cost100
Reliability100
Client compatibility70

What to fix (4)

1 tool(s) have parameters with no type (no type/enum/anyOf/$ref).

Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →

Tools: oxyo_causal_infer

Negotiates MCP 2025-03-26. Structured output, tool output schemas and elicitation arrived in 2025-06-18.

Upgrade the MCP SDK and negotiate 2025-06-18 or newer. How to fix →

No tool declares an outputSchema.

Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →

In the last 30 days: 0 tool(s) removed and 2 schema change(s).

Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →

Auto-fix: 1 corrected tool definition

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.eno654%2Foxyo-mcp/fixes

oxyo_causal_infer 1 change
{
  "name": "oxyo_causal_infer",
  "description": "Query the root-cause graph to trace upstream failure sources (`diagnose`), downstream blast radius (`intervene`), simulated interventions (`do_calculus`, `counterfactual`), continuous-metric what-if estimation (`continuous_counterfactual`, separating hidden disturbance from action effect with identifiability and discontinuity guards), or highest-value diagnostic checks (`experiments`). Use to analyze recorded dependencies; call `oxyo_causal_record` to add new edges.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "do": {
        "type": "object",
        "description": "Optional forced node state map {node: 0.0..1.0} for 'do_calculus' or 'counterfactual'."
      },
      "mode": {
        "enum": [
          "intervene",
          "diagnose",
          "do_calculus",
          "counterfactual",
          "continuous_counterfactual",
          "experiments"
        ],
        "type": "string",
        "default": "intervene",
        "description": "Analysis mode: 'diagnose' (causes), 'intervene' (effects), 'do_calculus', 'counterfactual', 'continuous_counterfactual' (numeric what-if), or 'experiments'."
      },
      "scope": {
        "type": "string",
        "description": "Optional project/repo scope filter."
      },
      "entity": {
        "type": "string",
        "description": "Target symptom (for 'diagnose') or upstream node (for 'intervene') to analyze."
      },
      "factual": {
        "type": "object",
        "description": "Optional observed node state map {node: 0.0..1.0} for 'counterfactual' queries."
      },
      "horizon": {
        "type": "number",
        "description": "Optional transition duration horizon for short-time error-scale reporting."
      },
      "alt_pred": {
        "description": "Baseline predicted numeric outcome under the alternative action for 'continuous_counterfactual'.",
        "type": "string"
      },
      "max_hops": {
        "type": "integer",
        "default": 4,
        "description": "Maximum multi-hop traversal depth across the causal graph (1..8)."
      },
      "metric_name": {
        "type": "string",
        "default": "outcome",
        "description": "Optional metric label (e.g. 'latency_ms', 'cost_usd') for 'continuous_counterfactual'."
      },
      "factual_pred": {
        "description": "Baseline predicted numeric outcome under the factual action for 'continuous_counterfactual'.",
        "type": "string"
      },
      "action_distance": {
        "type": "number",
        "description": "Optional distance between factual and alternative actions for error-bound reporting."
      },
      "observed_outcome": {
        "description": "Observed factual numeric scalar or vector outcome for 'continuous_counterfactual'.",
        "type": "string"
      },
      "has_discontinuity": {
        "type": "boolean",
        "default": false,
        "description": "Set true if the transition crossed a sharp jump or discrete regime break."
      },
      "is_multiplicative": {
        "type": "boolean",
        "default": false,
        "description": "Set true if the unobserved disturbance scales/multiplies the action rather than acting additively."
      },
      "interaction_bound_k": {
        "type": "number",
        "description": "Optional action-disturbance interaction Lipschitz bound."
      },
      "persistent_disturbance": {
        "type": "boolean",
        "default": true,
        "description": "Whether the unobserved disturbance persists for the counterfactual event (default true)."
      }
    }
  },
  "annotations": {
    "title": "Infer Root Causes & Blast Radius",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.eno654/oxyo-mcp"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/io.github.eno654/oxyo-mcp"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live.

Badge for your README

Shows whether the server is live and its agent-readiness score; it updates within the hour.

MCP server status

Markdown
[![MCP server status](https://glimind.com/badge/mcp-registry%2Fio.github.eno654%2Foxyo-mcp.svg)](https://glimind.com/server/mcp-registry%2Fio.github.eno654%2Foxyo-mcp?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fio.github.eno654%2Foxyo-mcp?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.eno654%2Foxyo-mcp.svg" alt="MCP server status"></a>

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:dfc16fd03b470f10…, first seen 2026-11-21, included at leaf 375538 of 384,710. Version history · verify what your client received.

Tools (19)

Compare: most reliable memory servers · most reliable ml servers · most reliable devops servers · most reliable code servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp?ref=install-server"
    }
  }
}

FAQ

Is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server down right now?

As of 2026-11-22 17:22 UTC, the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 100% of Glimind's liveness checks.

How many tools does Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server provide?

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server advertises 19 tools, including memory_retrieve, memory_store, oxyo_belief_revisions, oxyo_causal_infer, oxyo_causal_record.

How do I install Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server?

Point your MCP client at this streamable-http endpoint: https://oxyo.si/mcp

Is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server safe to connect to an AI agent?

Glimind scanned all 15 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve