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.blackaxgit/agent-mcp-hub

NPM · AGENT-MCP-HUB · SCANNED SEP 20

One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

Available components

0 this week 81 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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2660 tokens (~295/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 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
Install

How do I install the io.github.blackaxgit/agent-mcp-hub server?

io.github.blackaxgit/agent-mcp-hub runs locally as an npm package, launched with npx -y agent-mcp-hub. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · agent-mcp-hub

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

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 17 Sept 26 −2
    • Security disclosure: fail → unverified functional
    • 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 0
    • Security disclosure: unverified → fail functional
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 0
    • Security disclosure: fail → unverified functional
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 npm/agent-mcp-hub@0.6.1

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~2,660 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
agy ~355

Google Antigravity (agy) — Gemini-powered autonomous coding agent that reads and edits files to implement, refactor, and fix code. Runs the `agy` CLI non-interactively in `cwd` — it can read and edit files there and may take time or use the agent's own model quota — and returns its output. On common failures returns a classified, actionable error (not installed / not authenticated with the exact login command / not configured / timed out / busy / output-limit); other non-zero exits return a clipped stderr/stdout tail. Check availability with list_agents first.

NameTypeReqDescription
cwdstringWorking directory for the CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox — the agent may read/edit any files it can access.
idleTimeoutMsintegerIdle/inactivity timeout in milliseconds — the run is killed only if the agent produces NO output for this long (the timer resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id passed through to the CLI, overriding that CLI's configured/default model (e.g. "o3"). Model names are agent-specific. Must match [A-Za-z0-9][A-Za-z0-9._:/-]{0,127} — a flag-shaped…
promptstringyesThe task or question for the agent, in natural language.
timeoutMsintegerTotal runtime cap in milliseconds — the hard upper bound on the whole run once the CLI starts (excludes time queued behind the concurrency limit); the process group is killed if exceeded (default 180…

No output schema declared.

No examples provided.

claude ~347

Claude Code — Anthropic's coding agent for complex implementation, refactoring, and code review. Runs the `claude` CLI non-interactively in `cwd` — it can read and edit files there and may take time or use the agent's own model quota — and returns its output. On common failures returns a classified, actionable error (not installed / not authenticated with the exact login command / not configured / timed out / busy / output-limit); other non-zero exits return a clipped stderr/stdout tail. Check availability with list_agents first.

NameTypeReqDescription
cwdstringWorking directory for the CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox — the agent may read/edit any files it can access.
idleTimeoutMsintegerIdle/inactivity timeout in milliseconds — the run is killed only if the agent produces NO output for this long (the timer resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id passed through to the CLI, overriding that CLI's configured/default model (e.g. "o3"). Model names are agent-specific. Must match [A-Za-z0-9][A-Za-z0-9._:/-]{0,127} — a flag-shaped…
promptstringyesThe task or question for the agent, in natural language.
timeoutMsintegerTotal runtime cap in milliseconds — the hard upper bound on the whole run once the CLI starts (excludes time queued behind the concurrency limit); the process group is killed if exceeded (default 180…

No output schema declared.

No examples provided.

codex ~359

OpenAI Codex — a terminal coding agent (GPT/o-series) that autonomously reads and edits files to implement, refactor, and fix code. Runs the `codex` CLI non-interactively in `cwd` — it can read and edit files there and may take time or use the agent's own model quota — and returns its output. On common failures returns a classified, actionable error (not installed / not authenticated with the exact login command / not configured / timed out / busy / output-limit); other non-zero exits return a clipped stderr/stdout tail. Check availability with list_agents first.

NameTypeReqDescription
cwdstringWorking directory for the CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox — the agent may read/edit any files it can access.
idleTimeoutMsintegerIdle/inactivity timeout in milliseconds — the run is killed only if the agent produces NO output for this long (the timer resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id passed through to the CLI, overriding that CLI's configured/default model (e.g. "o3"). Model names are agent-specific. Must match [A-Za-z0-9][A-Za-z0-9._:/-]{0,127} — a flag-shaped…
promptstringyesThe task or question for the agent, in natural language.
timeoutMsintegerTotal runtime cap in milliseconds — the hard upper bound on the whole run once the CLI starts (excludes time queued behind the concurrency limit); the process group is killed if exceeded (default 180…

No output schema declared.

No examples provided.

cursor ~352

Cursor Agent (cursor-agent) — Cursor's repo-aware autonomous coding agent; implements and edits code from a natural-language task. Runs the `cursor-agent` CLI non-interactively in `cwd` — it can read and edit files there and may take time or use the agent's own model quota — and returns its output. On common failures returns a classified, actionable error (not installed / not authenticated with the exact login command / not configured / timed out / busy / output-limit); other non-zero exits return a clipped stderr/stdout tail. Check availability with list_agents first.

NameTypeReqDescription
cwdstringWorking directory for the CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox — the agent may read/edit any files it can access.
idleTimeoutMsintegerIdle/inactivity timeout in milliseconds — the run is killed only if the agent produces NO output for this long (the timer resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id passed through to the CLI, overriding that CLI's configured/default model (e.g. "o3"). Model names are agent-specific. Must match [A-Za-z0-9][A-Za-z0-9._:/-]{0,127} — a flag-shaped…
promptstringyesThe task or question for the agent, in natural language.
timeoutMsintegerTotal runtime cap in milliseconds — the hard upper bound on the whole run once the CLI starts (excludes time queued behind the concurrency limit); the process group is killed if exceeded (default 180…

No output schema declared.

No examples provided.

list_agents ~120

List the wrapped coding-agent CLIs and whether each can actually run (edits nothing). Each entry reports `installed` (binary resolves on PATH with the exec bit) and `usable` (a probe succeeded), plus a `reason` when it cannot run; `available` mirrors `usable`. A CLI can be installed but unusable — codex exits 0 from `--version` even when its home is unwritable and no real run can succeed — so prefer `usable`. Read-only; call this first to choose an agent before delegating.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

opencode ~370

OpenCode — an open-source, provider-agnostic coding agent for agentic code changes; its model defaults to the user's opencode config unless a model is provided. Prompts must not start with '-'. Runs the `opencode` CLI non-interactively in `cwd` — it can read and edit files there and may take time or use the agent's own model quota — and returns its output. On common failures returns a classified, actionable error (not installed / not authenticated with the exact login command / not configured / timed out / busy / output-limit); other non-zero exits return a clipped stderr/stdout tail. Check availability with list_agents first.

NameTypeReqDescription
cwdstringWorking directory for the CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox — the agent may read/edit any files it can access.
idleTimeoutMsintegerIdle/inactivity timeout in milliseconds — the run is killed only if the agent produces NO output for this long (the timer resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id passed through to the CLI, overriding that CLI's configured/default model (e.g. "o3"). Model names are agent-specific. Must match [A-Za-z0-9][A-Za-z0-9._:/-]{0,127} — a flag-shaped…
promptstringyesThe task or question for the agent, in natural language.
timeoutMsintegerTotal runtime cap in milliseconds — the hard upper bound on the whole run once the CLI starts (excludes time queued behind the concurrency limit); the process group is killed if exceeded (default 180…

No output schema declared.

No examples provided.

ping ~28

Liveness check for agent-mcp-hub — returns "pong". Read-only, no side effects.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

review_change ~341

Run the `runner` agent in `cwd` (which edits files), capture the concrete `git diff` of the change, then have the `reviewer` agent judge it and return a PASS/WARN/FAIL verdict along with the runner output, the diff, and the review. Requires a git worktree. Newly-created (untracked) files are reviewed by their contents too (bounded per file), not just by name. The diff may include pre-existing changes if the worktree was already dirty.

NameTypeReqDescription
cwdstringyesGit working tree the runner operates in (REQUIRED)
modelstringFallback model for BOTH agents. Only useful when runner and reviewer are the same agent — model namespaces do not overlap, so one value cannot be valid for two different CLIs. For the cross-agent set…
promptstringyesTask or question to send to the runner agent
reviewerstringyesAdapter name of the agent that judges the change
reviewerModelstringModel for the REVIEWER agent, overriding `model`. Lets you review with a different engine/tier than the one that wrote the change.
runnerstringyesAdapter name of the agent that edits files
runnerModelstringModel for the RUNNER agent, overriding `model`. Use this (not `model`) when runner and reviewer are different agents.
timeoutMsintegerPer-agent timeout in ms

No output schema declared.

No examples provided.

run_all ~388

Fan the SAME prompt out to every enabled agent concurrently and return each agent's answer, labelled per agent — for comparing agents or cross-checking a result. Spawns every CLI (each can read/edit files in `cwd`) so it can be slow or use several agents' quotas; one confirmation covers the whole batch.

NameTypeReqDescription
cwdstringWorking directory for every CLI. Prefer an absolute path; a relative path resolves from the server process's cwd. Not a sandbox.
idleTimeoutMsintegerPer-agent idle/inactivity timeout in milliseconds — killed only if the agent produces NO output for this long (resets on each output chunk; default 300000 = 5 minutes).
modelstringOptional model id applied to EVERY agent as a fallback. Model namespaces do not overlap between agents, so a single value is usually valid for only one of them — prefer `models` for a fan-out. Must m…
modelsobjectPer-agent model overrides, e.g. {"codex":"o3","agy":"gemini-3.6-flash-low"}. Takes precedence over `model` for the agents named; any agent not listed falls back to `model`, then to its own CLI defaul…
promptstringyesThe task or question to send to every agent, in natural language.
timeoutMsintegerPer-agent TOTAL runtime cap in milliseconds once each CLI starts (process group killed if exceeded; default 1800000 = 30 minutes).

No output schema declared.

No examples provided.

Common questions

What is the io.github.blackaxgit/agent-mcp-hub server?

io.github.blackaxgit/agent-mcp-hub is listed in the public MCP registry as io.github.blackaxgit/agent-mcp-hub. One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents. This page covers its npm package (agent-mcp-hub).

Is the io.github.blackaxgit/agent-mcp-hub server safe to use?

io.github.blackaxgit/agent-mcp-hub scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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.blackaxgit/agent-mcp-hub server expose?

io.github.blackaxgit/agent-mcp-hub exposes 9 tools: ping, list_agents, codex, cursor, opencode, and 4 more. Their descriptions and schemas cost roughly 2,660 tokens of context every time the server is loaded.

Is the io.github.blackaxgit/agent-mcp-hub server still maintained?

io.github.blackaxgit/agent-mcp-hub 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.

What licence is the io.github.blackaxgit/agent-mcp-hub server under?

io.github.blackaxgit/agent-mcp-hub declares the MPL-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.