Skip to content

MCP servers › io.github.Eno654 › oxyo-mcp

MCP server · registry snapshot 2026-11-12 · last checked 2026-11-13

oxyo-mcp MCP server

Registry name io.github.Eno654/oxyo-mcp

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% — the publisher's title

by Eno654 · GitHub account (the registry's namespace rule)repository: same ownerSource ↗PyPI ↗Website ↗

Cuts coding agent token burn up to 72% continuously via contradiction-free memory & verification. — the publisher's description

7 of 8 record checks metRead-only · tools listed 2026-11-12version 1.2.4JavaScriptMITstandard input/output, streamable HTTP15 tools

Summary

io.github.Eno654/oxyo-mcp is a remote and local MCP server listed in the official MCP registry at version 1.2.4, under the namespace of the GitHub account Eno654. Its linked repository, github.com/Eno654/oxyo-mcp, belongs to the same GitHub account. On 2026-11-12 ProtocolProbe connected to it in read-only mode and read its inventory: 15 tools, 0 resources and 0 prompts.

Record checks

7 of 8 record checks met · 1 does not apply

  • met: Registry entry is active and says how to run it
  • met: Source repository link opens
  • met: Repository is not archived
  • met: Code pushed to the repository in the 90 days before our check
  • not met: Repository publishes a security policy (SECURITY.md)
  • met: Package names its licence with a standard (SPDX) identifier
  • met: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • met: No known critical or high advisory in the package or its dependencies
  • #10,514 of 20,610 packages by monthly downloads, tied with 17 others
  • Not ranked by stars: 1 star (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote and local package
Transport
standard input/output, streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Package
PyPI · listed version current
License
MIT
Dependencies
no known high or critical advisories
Repository
public
Tools
15
Last tested
2026-11-12

Tool list size

6,647 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (15 tools). Counted with Anthropic's token counter on 2026-11-12, from the tool list we read on 2026-11-12. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-12 (oxyo.si), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.2.4).

Add to your client

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-12
Mode
read-only (no tool calls)
Latest version
1.2.4, published 2026-11-11 (registry, as of the 2026-11-12 snapshot)
First listed version
2026-11-11 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, all on 2026-11-11; 2 in the 90 days before the 2026-11-12 snapshot.
Most recent 2 versions
  • 1.2.4 · 2026-11-11
  • 1.2.3 · 2026-11-11
(versions still listed in the registry only)
Registry data
snapshot 2026-11-12
Package and repository
checked 2026-11-13
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-09, listed on 2026-11-12 with version 1.2.4 (published 2026-11-11).

Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12.

What it is

What does this server offer?

Observed inventory
15tools
0resources
0prompts

None of its 15 tools are described as changing anything. For 15 the reading was uncertain, so no mark is shown.

  • oxyo_session_pack

    “Load a compact session-start context capsule (<350 tokens) returning active contradiction-free project/global beliefs, recent actions, root-cause warnings, and verified skills.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    3 inputs
    • scopestring“Project or repository scope identifier (e.g.”
    • focusstring“Optional current task focus query used to rank relevant rules and warnings.”
    • auto_consolidateboolean“Automatically archive redundant older episodes when episode count exceeds threshold.”
  • oxyo_recall

    “Search persistent memory by keyword and meaning, returning compact episodic snippets, active contradiction-free beliefs, root-cause chains, and verified Python skills.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    7 inputs, 1 required
    • querystringrequired“Natural-language or keyword query to match against beliefs, episodes, and skills.”
    • scopestring“Optional project/repo scope filter (automatically includes 'global' rules).”
    • k_episodesinteger“Maximum number of matching episodic snippets to return (1..20).”
    • k_beliefsinteger“Maximum number of active beliefs to return (1..30).”
    • max_episode_charsinteger“Character cap per returned episode snippet before head/tail compaction.”
    • full_episodesboolean“Return uncompacted full episode text instead of token-budgeted snippets.”
    • reinforce_idsarray“Optional memory item IDs from prior recalls that proved helpful on the task.”
  • oxyo_remember_episode

    “Append a timestamped task action, architectural decision, or observation to episodic history, returning the stored episode metadata.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    5 inputs, 1 required
    • contentstringrequired“Concise summary of the completed action, decision, or technical observation.”
    • kindstring“Event category ('action' for changes made, 'observation' for findings, 'user' for requests).”
    • scopestring“Project/repo scope where this episode applies (defaults to 'global').”
    • importancenumber“Base retention priority score between 0.0 (trivial) and 1.0 (critical milestone).”
    • use_neural_salienceboolean“Automatically calibrate retention priority based on novelty and information density.”
  • oxyo_remember_belief

    “Persist a durable fact, project rule, or user preference, automatically deduplicating paraphrases and superseding contradicted older 1:1 claims while preserving 1:N additive facts.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • claimstringrequired“Single self-contained factual statement, configuration rule, or user preference.”
    • confidencenumber“Epistemic certainty score from 0.0 (tentative) to 1.0 (verified ground truth).”
    • scopestring“Project/repo scope for conflict resolution and recall (defaults to 'global').”
  • oxyo_belief_revisions

    “Retrieve the immutable audit log of superseded beliefs paired with the newer claims that replaced them.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • limitinteger“Maximum number of recent belief revision entries to return (1..100).”
  • oxyo_causal_record

    “Record or reinforce a directed cause-and-effect link in the project root-cause graph, returning updated edge confidence and observation counts.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    6 inputs, 2 required
    • causestringrequired“Upstream trigger component, config change, or condition (e.g.”
    • actionstring“Relationship verb connecting cause to effect (e.g.”
    • effectstringrequired“Downstream symptom, failure mode, or system outcome (e.g.”
    • polarityinteger“Direction of influence: 1 if cause increases/triggers effect, -1 if it prevents/reduces it.”
    • succeededboolean“True if the link was confirmed in practice; False to down-weight a refuted hypothesis.”
    • scopestring“Project/repo scope for isolating causal graphs (defaults to 'global').”
  • oxyo_causal_infer

    “Query the root-cause graph to trace upstream failure sources (`diagnose`), downstream blast radius (`intervene`), simulated interventions (`do_calculus`, `counterfactual`), or highest-value diagnosti…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    6 inputs
    • entitystring“Target symptom (for 'diagnose') or upstream node (for 'intervene') to analyze.”
    • modestring“Analysis mode: 'diagnose' (causes), 'intervene' (effects), 'do_calculus', 'counterfactual', or 'experiments'.”
    • doobject“Optional forced node state map {node: 0.0..1.0} for 'do_calculus' or 'counterfactual'.”
    • factualobject“Optional observed node state map {node: 0.0..1.0} for 'counterfactual' queries.”
    • max_hopsinteger“Maximum multi-hop traversal depth across the causal graph (1..8).”
    • scopestring“Optional project/repo scope filter.”
  • oxyo_verify_python

    “Execute deterministic Python math, financial `Decimal`, or algorithmic checks inside an isolated zero-network sandbox (`RESULT = ...`), returning exact `RESULT`, stdout, and optional boundary-fuzz re…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    5 inputs, 1 required
    • codestringrequired“Self-contained standard-library Python code assigning final output to `RESULT = ...`.”
    • timeout_snumber“Maximum execution wall-time in seconds before termination (0.5..10.0).”
    • fuzzboolean“Run automated boundary/edge-case property fuzzing and determinism checks.”
    • entrypointstring“Optional top-level function name in `code` to target during boundary fuzzing.”
    • invariantsarray“Optional Python boolean expressions (e.g.”
  • oxyo_skill_register

    “Validate and persist a reusable Python function into the skill library only after 100% of supplied `test_cases` pass in isolation, returning verification status.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    7 inputs, 5 required
    • namestringrequired“Unique snake_case identifier for the reusable skill.”
    • entrypointstringrequired“Top-level Python function name inside `code` invoked when running the skill.”
    • descriptionstringrequired“Clear summary of inputs, algorithm, and return value for future discovery.”
    • codestringrequired“Pure standard-library Python source defining the `entrypoint` function.”
    • test_casesarrayrequired“Non-empty list of test objects {'args': [...], 'expected': ...} verified before saving.”
    • uses_skillsarray“Optional names of previously registered skills composed by this function.”
    • share_collectiveboolean“Allow sharing anonymized verified utility patterns with the collective skill pool.”
  • oxyo_skill_invoke

    “List registered Python skills (`action='list'`) or execute a named skill (`action='execute'`) with arguments in isolation, returning its deterministic return value.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • actionstring“Choose 'list' to browse available skills or 'execute' to run `name` with `args`.”
    • namestring“Registered skill name to execute (required when action='execute').”
    • argsarray“Positional JSON arguments passed to the skill entrypoint when action='execute'.”
  • oxyo_consolidate

    “Compact older episodic history by archiving redundant entries and promoting recurring patterns while preserving the latest episodes, returning compaction statistics.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    2 inputs
    • scopestring“Optional project/repo scope to compact (consolidates all scopes if omitted).”
    • keep_recentinteger“Number of newest episodes in the scope kept verbatim without compaction.”
  • oxyo_goal

    “Manage persistent multi-session task dependency graphs (`create`, `decompose`, `next`, `update`, `tree`), returning unblocked next tasks and automatically propagating failure blockers.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    15 inputs
    • actionstring“Operation: 'create' goal, 'decompose' into subgoals, 'next' unblocked tasks, 'update' status, or 'tree'.”
    • goal_idstring“Target goal ID for 'decompose', 'update', or subtree inspection.”
    • parent_idstring“Optional parent goal ID when creating a nested sub-goal.”
    • titlestring“Concise actionable goal title (required when action='create').”
    • acceptance_criteriastring“Concrete verification condition defining when the goal is complete.”
    • depends_onarray“List of prerequisite goal IDs that must complete before this goal unblocks.”
    • prospective_triggerstring“Optional context cue or file/topic pattern that surfaces this goal automatically.”
    • prioritynumber“Scheduling priority from 0.0 (low) to 1.0 (urgent) used to rank 'next' tasks.”
    • subgoalsarray“Child goal specs [{'title': ..., 'acceptance_criteria': ...}] when action='decompose'.”
    • chain_sequentiallyboolean“Automatically wire each decomposed subgoal to depend on the preceding subgoal.”
    • statusstring“New lifecycle state applied to `goal_id` when action='update'.”
    • evidencestring“Verification output, commit hash, or test summary recorded on status update.”
    • failure_causestring“Root-cause label logged to the causal graph when updating status to 'failed'.”
    • scopestring“Optional project/repo scope for isolating goal trees.”
    • limitinteger“Maximum number of unblocked tasks returned when action='next'.”
Show 3 more tools
  • oxyo_sleep_abstract

    “Distill verified code execution traces into tested, reusable functions in the persistent skill vault while compacting older episodic logs.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    4 inputs
    • scopestring“Optional project/repo scope to process.”
    • keep_recentinteger“Number of newest episodes retained verbatim during memory compaction.”
    • max_new_skillsinteger“Maximum number of newly synthesized skills promoted in one pass (1..10).”
    • tracesarray“Optional verified trace objects [{'prompt': ..., 'verified_code': ...}] to abstract.”
  • oxyo_prove_constraints

    “Solve bounded discrete constraint systems (`action='satisfy'` with optional `minimize`/`maximize`) or prove universal invariants (`action='prove'`, returning a formal proof or minimal counterexample).”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    7 inputs, 1 required
    • actionstring“Choose 'prove' to verify `assumptions => claim` universally, or 'satisfy' to find an assignment.”
    • variablesobjectrequired“Bounded variable domain map, e.g.”
    • claimstring“Boolean invariant expression that must hold across all valid states (for action='prove').”
    • assumptionsarray“Precondition boolean expressions constraining valid input states (for action='prove').”
    • constraintsarray“Boolean constraint expressions that a solution must satisfy (for action='satisfy').”
    • objectivestring“Optional arithmetic expression to optimize across valid assignments (for action='satisfy').”
    • sensestring“Optimization direction ('minimize' or 'maximize') when `objective` is provided.”
  • oxyo_self_play_distill

    “Generate and deterministically verify synthetic parametric coding challenges in isolation, returning curated verified solution traces and optionally promoting reusable helper skills.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    7 inputs
    • run_self_playboolean“Generate and verify new parametric problems before exporting traces.”
    • difficultyinteger“Problem complexity tier from 1 (foundational) to 5 (advanced).”
    • max_problemsinteger“Number of synthetic problems to generate and verify in this run (1..8).”
    • max_per_familyinteger“Maximum verified traces retained per problem family during curation.”
    • export_corpusboolean“Export the curated verified trace corpus after problem verification.”
    • promote_skillsboolean“Automatically register verified reusable helper functions into the skill library.”
    • seedinteger“Optional integer RNG seed for reproducible problem generation.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-12.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 81
Tools with a description
100% of 15
Typical description length
268 characters

The tool set

Counted from the listing

Tools
15
Size of the list
about 4,710 tokens for an agent to load (characters ÷ 4)
Naming
15 of 15 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 15 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the PyPI package oxyo-mcp

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
  "mcpServers": {
    "oxyo-mcp": {
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ]
    }
  }
}
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "oxyo-mcp": {
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ]
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "oxyo-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ]
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"oxyo-mcp","type":"stdio","command":"uvx","args":["oxyo-mcp==1.2.4"]}'
Claude Code
claude mcp add --transport stdio oxyo-mcp -- uvx oxyo-mcp==1.2.4
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "oxyo-mcp": {
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "oxyo-mcp": {
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ]
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.oxyo-mcp]
command = "uvx"
args = ["oxyo-mcp==1.2.4"]
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "oxyo-mcp": {
      "command": "uvx",
      "args": [
        "oxyo-mcp==1.2.4"
      ]
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- uvx oxyo-mcp==1.2.4
  • Optional settings the entry also lists (left out above): OXYO_API_KEY.
  • This runs the publisher's code on your machine (uvx). Read its README first.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-12 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://oxyo.si/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "oxyo-mcp": {
      "url": "https://oxyo.si/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "oxyo-mcp": {
      "type": "http",
      "url": "https://oxyo.si/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"oxyo-mcp","type":"http","url":"https://oxyo.si/mcp"}'
Claude Code
claude mcp add --transport http oxyo-mcp https://oxyo.si/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "oxyo-mcp": {
      "type": "streamableHttp",
      "url": "https://oxyo.si/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "oxyo-mcp": {
      "httpUrl": "https://oxyo.si/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.oxyo-mcp]
url = "https://oxyo.si/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "oxyo-mcp": {
      "url": "https://oxyo.si/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://oxyo.si/mcp --transport http
  • Optional settings the entry also lists (left out above): Authorization.
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists
1.2.4
Latest stable
1.2.4
Status
current
Withdrawn
no

Source: pypi.org · 2026-11-13. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

critical0high0moderate0low0

Counted in the full dependency tree as resolved on 2026-11-12 (OSV.dev; each bar counts advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity
sha256-44f2e6558abd67746…
License
MIT

Source: the package registry · 2026-11-13.

Usage

Downloads
371 in the last month

Source: pypistats.org · 2026-11-13.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

Registry entry

  • Same package in other registry entries. No other registry entry lists this entry's npm or PyPI package at a newer version. Source: own registry snapshot · read 2026-11-12.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-12. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-12. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-12. Source: read 2026-11-12.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-12. Source: read 2026-11-12.

Own host

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint oxyo.si/mcpSession openedmatchesour test · 2026-11-12
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-12
Version 1.2.4 on PyPIExists and can be installedmatchesPyPI · 2026-11-13
Repository github.com/Eno654/oxyo-mcpOpens publiclymatchesapi.github.com · 2026-11-13

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
io.github.Eno654
GitHub owner
a personal account (Eno654)
Repository
github.com/Eno654/oxyo-mcp
Stars
1
Repository age
0–30 days
Last push
0–30 days ago
Archived
no
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-11-13; security policy read from GitHub · 2026-11-12.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

7 of 8 record checks met · 1 does not apply

  • #10,514 of 20,610 packages by monthly downloads, tied with 17 others
  • Not ranked by stars: 1 star (ranked from 10)
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • MetSource repository link opensThe linked GitHub repository is public.
  • MetRepository is not archivedNot archived.
  • MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
  • Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
  • MetPackage names its licence with a standard (SPDX) identifierMIT
  • MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
  • Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
  • MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-13 (security policy 2026-11-12). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about io.github.Eno654/oxyo-mcp

Answered from the data above

Who publishes io.github.Eno654/oxyo-mcp?

The registry ties the namespace io.github.Eno654 to the GitHub account Eno654; only its owner can publish under it. Its linked repository, github.com/Eno654/oxyo-mcp, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.

Is io.github.Eno654/oxyo-mcp safe to install?

We do not rate servers as safe or unsafe. 7 of its 8 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.Eno654/oxyo-mcp need an API key or sign-in?

It opened a session without any credential on 2026-11-12. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.Eno654/oxyo-mcp been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Does io.github.Eno654/oxyo-mcp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 1.2.4, the latest stable release on PyPI.

Where is the source code of io.github.Eno654/oxyo-mcp?

In github.com/Eno654/oxyo-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (no operator permission)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-12
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 4
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-11-12, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 715 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 15 tools, 0 resources, 0 prompts.
  4. 3,832 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-12; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
api.github.com · 2026-11-12
Hosting type
registry · 2026-11-12
MCP capability
tools
our test · 2026-11-12
Transport
standard input/output, streamable HTTP
registry · 2026-11-12
Required credentials
none declared
registry · 2026-11-12 · no declaration is not a guarantee
Package registry
registry · 2026-11-12
Freshness
0–30 days
registry updatedAt · 2026-11-12
Lifecycle status
registry · 2026-11-12
License class
package registry · 2026-11-13
Integrity hash
declared (sha256)
package registry · 2026-11-13
Signature / provenance
does not apply
PyPI publishes no registry signature or attestation equivalent to npm dist.signatures
Dependency advisories
none known
OSV.dev · 2026-11-12
Popularity
371 downloads a month
package registry · 2026-11-13
Publisher signals
owner: a personal account · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-11-13
Maintenance
api.github.com · 2026-11-13
Environment
either (remote or your machine)
where it runs, from the hosting type · 2026-11-12

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.Eno654/oxyo-mcp: MCP server record.” Data checked 2026-11-13. https://protocolprobe.com/mcp/servers/io.github.Eno654/oxyo-mcp

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 7 of 8 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.Eno654/oxyo-mcp)](https://protocolprobe.com/mcp/servers/io.github.Eno654/oxyo-mcp)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology