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.

ContextOS — Powered Exoskeleton for AI Coding

OCI · GHCR.IO/YUBINBIN32-OPS/CONTEXTOS:2.2.2 · SCANNED SEP 20

Powered exoskeleton for AI coding: auto-governs context via MCP to cut 90%+ context waste.

33 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency35
Schema Quality & AI Usability57
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1086 tokens (~90/item across 12 items; 12 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 2 categories

Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the ContextOS — Powered Exoskeleton for AI Coding MCP server?

ContextOS — Powered Exoskeleton for AI Coding runs locally as a container image, launched with docker run --rm -i ghcr.io/yubinbin32-ops/contextos:2.2.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/yubinbin32-ops/contextos:2.2.2

# add to Claude Code
claude mcp add yubinbin32-ops-contextos -- docker run --rm -i ghcr.io/yubinbin32-ops/contextos:2.2.2
// .cursor/mcp.json
{
  "mcpServers": {
    "yubinbin32-ops-contextos": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/contextos:2.2.2"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "yubinbin32-ops-contextos": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/contextos:2.2.2"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add yubinbin32-ops-contextos -- docker run --rm -i ghcr.io/yubinbin32-ops/contextos:2.2.2
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "yubinbin32-ops-contextos": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/contextos:2.2.2"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  yubinbin32-ops-contextos:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/yubinbin32-ops/contextos:2.2.2"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "yubinbin32-ops-contextos": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/contextos:2.2.2"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "yubinbin32-ops-contextos": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/contextos:2.2.2"
      ]
    }
  }
}
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.

  • 18 Sept 26 33

    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 20 Sept 2026 · Analysed oci/ghcr.io/yubinbin32-ops/contextos:2.2.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 12 exposed · ~985 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
block ~70

Manage code functional Blocks. Blocks MUST bind to real code artifacts; ghost blocks are strictly rejected.

NameTypeReqDescription
actionstringyes
blockDataobject
formatstring
idstring
projectRootstring
querystring

No output schema declared.

No examples provided.

chain ~73

Feature chains and dependency links. Link kind reflects true semantics: depends_on, calls, imports, implements.

NameTypeReqDescription
actionstringyes
chainDataobject
formatstring
idstring
linkDataobject
projectRootstring

No output schema declared.

No examples provided.

code ~122

Code Gateway: read outline first, surgical read by symbol or line range, surgical edit with automatic re-anchoring, symbol search, and create new files with AST registration.

NameTypeReqDescription
actionstringyes
contentstring
endLinenumber
formatstring
pathstring
projectRootstring
querystring
replacementContentstring
selector
startLinenumber
targetContentstring

No output schema declared.

No examples provided.

contextos_doctor ~30

Diagnose ContextOS environment, storage routing, and editor integrations.

NameTypeReqDescription
projectRootstring

No output schema declared.

No examples provided.

contextos_init ~95

Initialize or switch ContextOS mode (local or cloud) for a project. User only chooses mode; AI performs setup.

NameTypeReqDescription
cloudUrlstring
injectEditorsboolean
modestring
platformsarray
projectIdstring
projectRootstring
saveGlobalCloudboolean
tokenstring

No output schema declared.

No examples provided.

contextos_switch ~78

Losslessly switch project between Local (offline SQLite) and Cloud (Cloudflare Edge D1) modes, bidirectionally synchronizing all architecture data.

NameTypeReqDescription
cloudUrlstring
projectIdstring
projectRootstring
targetModestringyes
tokenstring

No output schema declared.

No examples provided.

knowledge ~86

Project knowledge management: categorized Rules and single-narrative project Decision (DECISION.md).

NameTypeReqDescription
actionstringyes
contentstring
formatstring
projectRootstring
ruleDataobject
ruleIdstring
sectionIdstring
sectionTitlestring

No output schema declared.

No examples provided.

os_context ~79

Project context gateway. Use action=brief on session start or resume; search to find entities; open to read an entity; reconcile to check external Git/JSON changes.

NameTypeReqDescription
actionstring
entityIdstring
formatstring
projectRootstring
querystring

No output schema declared.

No examples provided.

plan ~88

Manage delivery Plans, Phases and Plan Checkpoints (formal acceptance). Checkpoints belong strictly to Plans.

NameTypeReqDescription
actionstringyes
checkpointIdstring
evidenceRefstring
formatstring
idstring
passedboolean
planDataobject
projectRootstring

No output schema declared.

No examples provided.

process ~69

Manage long-running daemon background processes (dev servers, watchers). Stop terminates entire process group.

NameTypeReqDescription
actionstringyes
commandstring
grepstring
idstring
linesnumber
projectRootstring

No output schema declared.

No examples provided.

run_command ~74

Run finite shell command. Sanitizes terminal noise, saves raw logs out-of-context in .contextos/logs, and returns compressed receipt.

NameTypeReqDescription
commandstringyes
cwdstring
maxCharsnumber
projectRootstring
timeoutMsnumber

No output schema declared.

No examples provided.

task ~121

C-D-C-S development lifecycle task execution (draft -> active -> checking -> syncing -> completed). Task sync requires 100% Block coverage on working set files.

NameTypeReqDescription
actionstringyes
checkDataobject
formatstring
idstring
kindstring
projectRootstring
ruleIdstring
rulesarray
syncDataobject
taskDataobject
textstring

No output schema declared.

No examples provided.

Common questions

What is the ContextOS — Powered Exoskeleton for AI Coding MCP server?

ContextOS — Powered Exoskeleton for AI Coding is an MCP server listed in the public MCP registry as io.github.yubinbin32-ops/contextos. Powered exoskeleton for AI coding: auto-governs context via MCP to cut 90%+ context waste. This page covers its container image (ghcr.io/yubinbin32-ops/contextos:2.2.2).

Is the ContextOS — Powered Exoskeleton for AI Coding MCP server safe to use?

ContextOS — Powered Exoskeleton for AI Coding scores 33 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 ContextOS — Powered Exoskeleton for AI Coding MCP server expose?

ContextOS — Powered Exoskeleton for AI Coding exposes 12 tools: os_context, plan, task, block, chain, and 7 more. Their descriptions and schemas cost roughly 985 tokens of context every time the server is loaded.

Is the ContextOS — Powered Exoskeleton for AI Coding MCP server still maintained?

ContextOS — Powered Exoskeleton for AI Coding is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.