Skip to content
Agentmart
Submit a tool

Agentic-Ops Control Plane

Autonomous and governed SRE & MLOps control plane for AI agent platforms.

Connector by nolll77 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)Remote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nolll77-agentic-ops

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://agentic-ops-5ebv.onrender.com/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Autonomous and governed SRE & MLOps control plane for AI agent platforms.

Use cases: incident-response, monitoring-observability

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
8 read · 1 write · 0 delete · 1 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 10

Read from the source code; the running server may list different tools.

Read 8 · Look things up without changing anything.

  • evaluate_governance_policy
  • get_ledger_status
  • get_scenario_blueprint
  • inspect_control_plane_vitals
  • inspect_worm_trust_ledger
  • read_console_diagnostic
  • search_failure_taxonomy
  • verify_ledger_inclusion

Write 1 · Create, change, send or run things.

  • run_governed_incident_episode

Not yet classified 1 · We could not tell from the name and description.

  • poll_target_mlops_snapshot

Network hosts it talks to 1

  • agentic-ops-5ebv.onrender.com · found in remote endpoint, install command

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • evaluate_governance_policy

    Evaluates a proposed AI agent action against the deterministic PolicyEngine and the configured exact-name local inventory. Without a fresh local inventory, targets are denied. Returns ALLOW, REQUIRE_APPROVAL (Slack HITL), or DENY with exact rule IDs.

  • get_ledger_status

    Returns the cryptographic health and status of the WORM Trust Ledger: total sealed entries, RFC 6962 Merkle Root (SHA-256), linear hash chain continuity, and HMAC-SHA512 tamper signatures.

  • get_scenario_blueprint

    Retrieves the architectural specification from docs/mlops_simulation_scenarios_registry.md and/or the executable YAML scenario contract from tests/scenarios/data/*.yaml.

  • inspect_control_plane_vitals

    Returns real-time health, socket status (Redis :6379, Tailscale SOCKS5 :1055), Linux cgroup v2 memory telemetry, and active PolicyBundle version hash.

  • inspect_worm_trust_ledger

    Audits the append-only WORM Trust Ledger (ledger.jsonl), verifies the full SHA-256 linear hash chain and HMAC-SHA512 signatures via EvidenceStore.verify_chain(), and returns sealed episodes.

  • poll_target_mlops_snapshot

    Executes a 100% Read-Only HTTP GET pull collection via CacPullCollector across the 5 observability endpoints of the target MLOps platform (jakatt/cac_mlops) over the Tailscale SOCKS5 mesh.

  • read_console_diagnostic

    Reads and executes any live diagnostic phase from the Agentic-Ops Web Console (/console). Returns the compact pytest PASSED results at the top followed by the color-coded cognitive pedagogical guide ([GUIDE:ROLE], [GUIDE:AGENT], [GUIDE:SLACK], [GUIDE:PROD], [GUIDE:HOW_IT_PASSES]).

  • run_governed_incident_episode

    Executes a full end-to-end governed incident episode through the PolicyEngine and seals the record into the local trust ledger. A fresh configured local inventory is required for an allowed target.

  • search_failure_taxonomy

    Searches the foundational 435 MLOps Failure Modes Taxonomy (docs/mlops_failure_modes_taxonomy.md) by keyword, risk ID, dimension, or symptom.

  • verify_ledger_inclusion

    Verifies an RFC 6962 binary Merkle Tree inclusion proof in O(log N) time. Can verify a local sealed episode by ID (e.g. EP-0001), or verify a complete external proof packet offline with zero disk I/O.

Signals

Stars
0
Forks
0
Open issues
6
Weekly downloads
1,458
Last commit
Oct 21, 2026 (7 days ago)
Last release
Oct 21, 2026 (7 days ago)
Last package publish
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.nolll77/agentic-ops
Version
0.1.14
Auth
Auth not stated
Packages
pypi agentic-ops
License
MIT
Repository
github.com/nolll77/agentic-ops
Website
agentic-ops-5ebv.onrender.com
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Agentic-Ops Control Plane MCP server. Agent Mart. https://agentmart.dev/connectors/nolll77-agentic-ops (last updated 2026-10-24)