Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72%

REMOTE · OXYO.SI · 2 COMPONENTS

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

−34 this week 36 Trust /100

Last scanned (18 hours ago)

Scores higher than 19% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Memory and Knowledge

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema blocked by authentication: the endpoint requires auth we don't have to read it. See how to fix → Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Tool Safety0
  • Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Capabilities0
  • Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. See how to fix → Unverified

Unverified: 6 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm. Claim this server and supply a read-only token to verify it and lift the score.

What we tested

Checks we ran (5)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC

Checks we could not complete (6)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Transport in Transport & Reachability (scores 0 for this)Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
  • Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema blocked by authentication: the endpoint requires auth we don't have to read it.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
  • Tool coverage in Tool Coverage (scores 0 for this)Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
  • Tool safety in Tool Safety (scores 0 for this)Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
  • Capabilities in Capabilities (scores 0 for this)Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 15 Nov 26 −34
    • Endpoint reachability: reachable → behind authorisation ▼ security
    • Stability: 0.10 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → unverified ▼ security
    • Authorization: partial → fail ▼ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: fail → unverified ▼ functional
    • First check of Schema quality: unverified functional
  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 0
    • “oxyo_skill_register” reworded the description of “share_collective” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 12 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 11 Nov 26 68

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://oxyo.si/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=oxyo.si CN=YE1,O=Let's Encrypt,C=US 8 Nov 2026 6 Feb 2027 ECDSA 256 ECDSA-SHA384 589e571c14f6a4b02d7c1447d74399b8e2e
SANs: *.oxyo.si, oxyo.si
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of oxyo.si. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
si. DS published 42378 13 Verified
oxyo.si. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On connection
HTTP status 403
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy upgrade-insecure-requests; frame-ancestors 'none'; base-uri 'self'; object-src 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=()

Protected resource metadata

Retrieved No
Problem No resource metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://oxyo.si/mcp Auth required 403
http (plaintext) http://oxyo.si/mcp HTTPS enforced 301 https://oxyo.si/mcp
MCP tools · 15 exposed · ~2,813 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
oxyo_belief_revisions ~72

Retrieve the immutable audit log of superseded beliefs paired with the newer claims that replaced them. Use to inspect historical rule changes and contradiction resolutions; use `oxyo_recall` for active beliefs.

NameTypeReqDescription
limitinteger–Maximum number of recent belief revision entries to return (1..100).

No output schema declared.

No examples provided.

oxyo_causal_infer ~243

Query the root-cause graph to trace upstream failure sources (`diagnose`), downstream blast radius (`intervene`), simulated interventions (`do_calculus`, `counterfactual`), or highest-value diagnostic checks (`experiments`). Use to analyze recorded dependencies; call `oxyo_causal_record` to add new edges.

NameTypeReqDescription
doobject–Optional forced node state map {node: 0.0..1.0} for 'do_calculus' or 'counterfactual'.
entitystring–Target symptom (for 'diagnose') or upstream node (for 'intervene') to analyze.
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).
modestring–Analysis mode: 'diagnose' (causes), 'intervene' (effects), 'do_calculus', 'counterfactual', or 'experiments'.
scopestring–Optional project/repo scope filter.

No output schema declared.

No examples provided.

oxyo_causal_record ~213

Record or reinforce a directed cause-and-effect link in the project root-cause graph, returning updated edge confidence and observation counts. Use when logging newly verified bug causes or system dependencies; use `oxyo_causal_infer` to query paths.

NameTypeReqDescription
actionstring–Relationship verb connecting cause to effect (e.g. 'causes', 'prevents', 'triggers').
causestringyesUpstream trigger component, config change, or condition (e.g. 'missing_db_index').
effectstringyesDownstream symptom, failure mode, or system outcome (e.g. 'checkout_timeout_504').
polarityinteger–Direction of influence: 1 if cause increases/triggers effect, -1 if it prevents/reduces it.
scopestring–Project/repo scope for isolating causal graphs (defaults to 'global').
succeededboolean–True if the link was confirmed in practice; False to down-weight a refuted hypothesis.

No output schema declared.

No examples provided.

oxyo_consolidate ~103

Compact older episodic history by archiving redundant entries and promoting recurring patterns while preserving the latest episodes, returning compaction statistics. Use for fast episodic cleanup; use `oxyo_sleep_abstract` when also distilling code traces into skills.

NameTypeReqDescription
keep_recentinteger–Number of newest episodes in the scope kept verbatim without compaction.
scopestring–Optional project/repo scope to compact (consolidates all scopes if omitted).

No output schema declared.

No examples provided.

oxyo_goal ~408

Manage persistent multi-session task dependency graphs (`create`, `decompose`, `next`, `update`, `tree`), returning unblocked next tasks and automatically propagating failure blockers. Use for multi-step project roadmaps across sessions; use `oxyo_remember_episode` for single-step logs.

NameTypeReqDescription
acceptance_criteriastring–Concrete verification condition defining when the goal is complete.
actionstring–Operation: 'create' goal, 'decompose' into subgoals, 'next' unblocked tasks, 'update' status, or 'tree'.
chain_sequentiallyboolean–Automatically wire each decomposed subgoal to depend on the preceding subgoal.
depends_onarray–List of prerequisite goal IDs that must complete before this goal unblocks.
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'.
goal_idstring–Target goal ID for 'decompose', 'update', or subtree inspection.
limitinteger–Maximum number of unblocked tasks returned when action='next'.
parent_idstring–Optional parent goal ID when creating a nested sub-goal.
prioritynumber–Scheduling priority from 0.0 (low) to 1.0 (urgent) used to rank 'next' tasks.
prospective_triggerstring–Optional context cue or file/topic pattern that surfaces this goal automatically.
scopestring–Optional project/repo scope for isolating goal trees.
statusstring–New lifecycle state applied to `goal_id` when action='update'.
subgoalsarray–Child goal specs [{'title': ..., 'acceptance_criteria': ...}] when action='decompose'.
titlestring–Concise actionable goal title (required when action='create').

No output schema declared.

No examples provided.

oxyo_prove_constraints ~254

Solve bounded discrete constraint systems (`action='satisfy'` with optional `minimize`/`maximize`) or prove universal invariants (`action='prove'`, returning a formal proof or minimal counterexample). Use for declarative constraint/invariant models; use `oxyo_verify_python` for general Python scripts.

NameTypeReqDescription
actionstring–Choose 'prove' to verify `assumptions => claim` universally, or 'satisfy' to find an assignment.
assumptionsarray–Precondition boolean expressions constraining valid input states (for action='prove').
claimstring–Boolean invariant expression that must hold across all valid 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.
variablesobjectyesBounded variable domain map, e.g. {'x': {'type': 'int', 'min': 0, 'max': 50}}.

No output schema declared.

No examples provided.

oxyo_recall ~208

Search persistent memory by keyword and meaning, returning compact episodic snippets, active contradiction-free beliefs, root-cause chains, and verified Python skills. Use for targeted mid-session lookups; call `oxyo_session_pack` instead at session cold start.

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

No output schema declared.

No examples provided.

oxyo_remember_belief ~138

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. Use for standing truths; use `oxyo_remember_episode` for transient chronological events.

NameTypeReqDescription
claimstringyesSingle 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').

No output schema declared.

No examples provided.

oxyo_remember_episode ~175

Append a timestamped task action, architectural decision, or observation to episodic history, returning the stored episode metadata. Use for chronological event logs; use `oxyo_remember_belief` instead for standing rules or facts.

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

No output schema declared.

No examples provided.

oxyo_self_play_distill ~198

Generate and deterministically verify synthetic parametric coding challenges in isolation, returning curated verified solution traces and optionally promoting reusable helper skills. Use for autonomous skill warm-up and trace curation; use `oxyo_verify_python` to check a single snippet.

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

No output schema declared.

No examples provided.

oxyo_session_pack ~132

Load a compact session-start context capsule (<350 tokens) returning active contradiction-free project/global beliefs, recent actions, root-cause warnings, and verified skills. Call once at cold start instead of `oxyo_recall`; use `oxyo_recall` for targeted mid-session searches.

NameTypeReqDescription
auto_consolidateboolean–Automatically archive redundant older episodes when episode count exceeds threshold.
focusstring–Optional current task focus query used to rank relevant rules and warnings.
scopestring–Project or repository scope identifier (e.g. 'oxyo', 'backend', or 'global').

No output schema declared.

No examples provided.

oxyo_skill_invoke ~131

List registered Python skills (`action='list'`) or execute a named skill (`action='execute'`) with arguments in isolation, returning its deterministic return value. Use to run already-verified skills; call `oxyo_skill_register` first to create a new skill.

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

No output schema declared.

No examples provided.

oxyo_skill_register ~218

Validate and persist a reusable Python function into the skill library only after 100% of supplied `test_cases` pass in isolation, returning verification status. Use to save new tested utilities; use `oxyo_skill_invoke` to list or execute existing skills.

NameTypeReqDescription
codestringyesPure standard-library Python source defining the `entrypoint` function.
descriptionstringyesClear summary of inputs, algorithm, and return value for future discovery.
entrypointstringyesTop-level Python function name inside `code` invoked when running the skill.
namestringyesUnique snake_case identifier for the reusable skill.
share_collectiveboolean–Opt-in to share anonymized verified utility patterns with the collective skill pool (default false; skills stay strictly private to your vault).
test_casesarrayyesNon-empty list of test objects {'args': [...], 'expected': ...} verified before saving.
uses_skillsarray–Optional names of previously registered skills composed by this function.

No output schema declared.

No examples provided.

oxyo_sleep_abstract ~138

Distill verified code execution traces into tested, reusable functions in the persistent skill vault while compacting older episodic logs. Use after coding milestones to extract skills; use `oxyo_consolidate` for episode cleanup without skill synthesis.

NameTypeReqDescription
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).
scopestring–Optional project/repo scope to process.
tracesarray–Optional verified trace objects [{'prompt': ..., 'verified_code': ...}] to abstract.

No output schema declared.

No examples provided.

oxyo_verify_python ~182

Execute deterministic Python math, financial `Decimal`, or algorithmic checks inside an isolated zero-network sandbox (`RESULT = ...`), returning exact `RESULT`, stdout, and optional boundary-fuzz results. Use for procedural Python verification; use `oxyo_prove_constraints` for declarative constraint solving.

NameTypeReqDescription
codestringyesSelf-contained standard-library Python code assigning final output to `RESULT = ...`.
entrypointstring–Optional top-level function name in `code` to target during boundary fuzzing.
fuzzboolean–Run automated boundary/edge-case property fuzzing and determinism checks.
invariantsarray–Optional Python boolean expressions (e.g. 'RESULT >= 0') asserted after execution.
timeout_snumber–Maximum execution wall-time in seconds before termination (0.5..10.0).

No output schema declared.

No examples provided.

Install

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

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… is a hosted endpoint at https://oxyo.si/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · oxyo.si

# add to Claude Code
claude mcp add --transport http eno654-oxyo-mcp 'https://oxyo.si/mcp'
Common questions

What is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server?

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… is an MCP server listed in the public MCP registry as io.github.Eno654/oxyo-mcp. Cuts coding agent token burn up to 72% continuously via contradiction-free memory & verification. This page covers its hosted endpoint (https://oxyo.si/mcp).

Is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server safe to use?

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… scores 36 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server expose?

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… exposes 15 tools: oxyo_session_pack, oxyo_recall, oxyo_remember_episode, oxyo_remember_belief, oxyo_belief_revisions, and 10 more. Their descriptions and schemas cost roughly 2,813 tokens of context every time the server is loaded.

Does the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server require authentication?

Yes. Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server still maintained?

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up… MCP server?

VerifyMCP ran 5 checks on Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up…, covering TLS certificate, Authorization, HTTPS, HSTS header and 1 more. 6 items could not be completed, a gap on our side rather than a finding about Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up…: Transport, Schema quality, Stability, Tool coverage and 2 more. 6 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.