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.

io.github.j7an/nexus-mcp

PYPI · NEXUS-MCP · SCANNED SEP 20

Invoke CLI agents (Codex, Claude, OpenCode) as MCP tools with parallel execution

Available components

−1 this week 65 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 Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 24 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2437 tokens (~76/item across 32 items; 20 tools + 12 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 41% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the io.github.j7an/nexus-mcp server?

io.github.j7an/nexus-mcp runs locally as a PyPI package, launched with uvx nexus-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · nexus-mcp

# add to Claude Code
claude mcp add j7an-nexus-mcp -- uvx nexus-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "j7an-nexus-mcp": {
      "command": "uvx",
      "args": [
        "nexus-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "j7an-nexus-mcp": {
      "command": "uvx",
      "args": [
        "nexus-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add j7an-nexus-mcp -- uvx nexus-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "j7an-nexus-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "nexus-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add j7an-nexus-mcp --command uvx --arg nexus-mcp
# ~/.hermes/config.yaml
mcp_servers:
  j7an-nexus-mcp:
    command: "uvx"
    args: ["nexus-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "j7an-nexus-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "nexus-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add j7an-nexus-mcp -t stdio -c uvx -a nexus-mcp
// mcp.json
{
  "mcpServers": {
    "j7an-nexus-mcp": {
      "command": "uvx",
      "args": [
        "nexus-mcp"
      ]
    }
  }
}
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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 −1
    • Tool coverage: 69% → 41% functional
    • Schema quality: fail → pass functional
    • MCP protocol: Implements a current MCP spec version (2026-07-28). functional
    • Package version: 1.0.3 → 1.1.0 functional
  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 −14
    • Malware scan: pass → unverified security
  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
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 pypi/nexus-mcp@1.1.0

Provenance No attestation

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

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 24 packages
Packages resolved 24
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 20 exposed · ~1,751 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
agent_backends ~33

Return deterministic descriptors with fresh availability for a workspace.

NameTypeReqDescription
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
itemsarray

No examples provided.

agent_cancel ~41

Request idempotent cancellation of one authorized durable job.

NameTypeReqDescription
job_idstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
cancel_requestedbooleanyes
completed_immediatelybooleanyes
event_committedbooleanyes
job_idstringyes
statestringyes

No examples provided.

agent_continue ~71

Queue a durable turn against an existing authorized session.

NameTypeReqDescription
config
context
file_refs
idempotency_key
promptstringyes
session_idstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
job_idstringyes
operationyes
session_id
statestring

No examples provided.

agent_diagnose ~54

Queue backend diagnostics without conditionally hiding the tool.

NameTypeReqDescription
backendstringyes
config
idempotency_key
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
job_idstringyes
operationyes
session_id
statestring

No examples provided.

agent_fork ~72

Fork an existing session when its backend advertises that capability.

NameTypeReqDescription
config
context
file_refs
idempotency_key
prompt
session_idstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
job_idstringyes
operationyes
session_id
statestring

No examples provided.

agent_list ~51

List one authorized page of durable jobs for an explicit workspace.

NameTypeReqDescription
cursor
limitinteger
states
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
itemsarray
next_cursor

No examples provided.

agent_respond ~55

Resolve one pending typed provider interaction for a durable job.

NameTypeReqDescription
input_idstringyes
job_idstringyes
responseyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
input_idstringyes
job_idstringyes
replayedboolean
statusstring

No examples provided.

agent_result ~44

Return the pending, succeeded, failed, or cancelled durable result variant.

NameTypeReqDescription
job_idstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
resultyes

No examples provided.

agent_review ~97

Queue a typed review when the session backend supports its target and delivery.

NameTypeReqDescription
config
context
deliverystring
file_refs
idempotency_key
instructions
session_idstringyes
targetobjectyesA bounded, provider-neutral target for a code review.
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
job_idstringyes
operationyes
session_id
statestring

No examples provided.

agent_start ~79

Start a durable session turn in an explicitly selected workspace.

NameTypeReqDescription
access_policystring
backendstringyes
config
context
file_refs
idempotency_key
promptstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
job_idstringyes
operationyes
session_id
statestring

No examples provided.

agent_status ~38

Return one authorized durable job status projection.

NameTypeReqDescription
job_idstringyes
workspaceobjectyesReference to exactly one durable workspace identity.
NameTypeReqDescription
backend_idstringyes
cancel_requestedboolean
completed_at
created_atstringyes
job_idstringyes
latest_event_sequenceinteger
operationyes
pending_inputsarray
phase
resolved_config
session_id
statestringyes
updated_atstringyes
workspace_idstringyes

No examples provided.

batch_prompt ~132

Send multiple prompts to CLI runners in parallel (primary tool). Fans out tasks server-side with asyncio.gather and a semaphore, enabling true parallel runner execution within a single MCP call. Single-task usage is perfectly valid — use prompt for convenience when sending one task.

NameTypeReqDescription
elicit
max_concurrencyintegerMax parallel runner invocations for this call (default: 3). The process worker maximum is 8; one call whose effective demand exceeds 8 is rejected.
tasksarrayyesList of AgentTask objects, each with cli, prompt, and optional fields.
NameTypeReqDescription
failedintegeryes
resultsarrayyes
succeededintegeryes
totalintegeryes

No examples provided.

clear_preferences ~25

Clear all persistent preferences, reverting to per-call defaults. Returns: Confirmation string.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

opencode_investigate ~51

Search project files and return the matching results. Chains GET /find → GET /file/content for up to max_files results.

NameTypeReqDescription
max_filesinteger
querystringyes
NameTypeReqDescription
resultstringyes

No examples provided.

opencode_session_review ~60

Review a session's messages and file changes. Chains GET /session/{id} → GET /session/{id}/message → GET /session/{id}/diff → GET /session/{id}/todo.

NameTypeReqDescription
session_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

opencode_set_provider_auth ~33

Set authentication credentials for a provider.

NameTypeReqDescription
credentialsobjectyes
provider_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

opencode_update_config ~23

Update OpenCode server configuration.

NameTypeReqDescription
configobjectyes
NameTypeReqDescription
resultstringyes

No examples provided.

prompt ~226

Send a prompt to a CLI runner as a background task. Returns immediately with a task ID. Client polls for results. This prevents timeouts for long operations (YOLO mode: 2-5 minutes).

NameTypeReqDescription
cliCLI runner name (e.g., "codex"). None triggers interactive selection.
contextOptional context metadata
elicit
execution_mode'default' (safe) or 'yolo'. None inherits session preference.
max_retriesMax retry attempts for transient errors (None inherits session preference).
modelModel name. None triggers interactive selection or uses CLI default.
output_limitMax output bytes (None inherits session preference or uses env default).
promptstringyesPrompt text to send to the runner
retry_base_delayBase delay seconds for exponential backoff (None inherits session/config).
retry_max_delayBackoff ceiling in seconds (None inherits session preference or config).
timeoutSubprocess timeout seconds (None inherits session preference or uses env default).
NameTypeReqDescription
resultstringyes

No examples provided.

set_model_tiers ~58

Save model tier classifications. Client sends sampling/benchmark results; server persists to backing store. Overwrites any previously saved tiers entirely.

NameTypeReqDescription
tiersobjectyesMapping of model name to tier ('quick', 'standard', 'thorough').
NameTypeReqDescription
resultstringyes

No examples provided.

set_preferences ~508

Set persistent preferences that apply to subsequent prompt/batch_prompt calls. Preferences persist across MCP sessions. Call again to update, or use clear_preferences to reset all fields at once. To clear a single field while keeping others, pass the corresponding clear_* flag: set_preferences(clear_model=True) # clears model, keeps execution_mode

NameTypeReqDescription
clear_confirm_high_retriesboolean
clear_confirm_large_batchboolean
clear_confirm_vague_promptboolean
clear_confirm_yoloboolean
clear_elicitboolean
clear_execution_modebooleanIf True, resets execution_mode to None regardless of the execution_mode argument.
clear_max_retriesbooleanIf True, resets max_retries to None regardless of the argument.
clear_modelbooleanIf True, resets model to None regardless of the model argument.
clear_output_limitbooleanIf True, resets output_limit to None regardless of the argument.
clear_retry_base_delaybooleanIf True, resets retry_base_delay to None.
clear_retry_max_delaybooleanIf True, resets retry_max_delay to None.
clear_timeoutbooleanIf True, resets timeout to None regardless of the argument.
confirm_high_retries
confirm_large_batch
confirm_vague_prompt
confirm_yolo
elicit
execution_modeDefault execution mode ('default' or 'yolo'). None retains the current value (use clear_execution_mode=True to reset).
max_retriesDefault max retry attempts for transient errors. None retains the current value (use clear_max_retries=True to reset).
modelDefault model name (e.g. 'gpt-5.2'). None retains the current value (use clear_model=True to reset).
output_limitDefault max output bytes per response. None retains the current value (use clear_output_limit=True to reset).
retry_base_delayDefault base delay seconds for exponential backoff. None retains the current value (use clear_retry_base_delay=True to reset).
retry_max_delayDefault max delay cap seconds for exponential backoff. None retains the current value (use clear_retry_max_delay=True to reset).
timeoutDefault subprocess timeout in seconds. None retains the current value (use clear_timeout=True to reset).
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the io.github.j7an/nexus-mcp server?

io.github.j7an/nexus-mcp is listed in the public MCP registry as io.github.j7an/nexus-mcp. Invoke CLI agents (Codex, Claude, OpenCode) as MCP tools with parallel execution. This page covers its PyPI package (nexus-mcp).

Is the io.github.j7an/nexus-mcp server safe to use?

io.github.j7an/nexus-mcp scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 io.github.j7an/nexus-mcp server expose?

io.github.j7an/nexus-mcp exposes 20 tools: batch_prompt, prompt, set_preferences, clear_preferences, set_model_tiers, and 15 more. Their descriptions and schemas cost roughly 1,751 tokens of context every time the server is loaded.

Is the io.github.j7an/nexus-mcp server still maintained?

io.github.j7an/nexus-mcp 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.