NAVIGATOR
Renders inventory data into Ansible files with credential references only, supporting Ansible automation workflows.
Supports Cisco network devices for allowlisted reads and approved change workflows through the change-ticket system.
Supports Fortinet devices as a connection method for allowlisted device reads.
Integrates with a local Ollama/OpenAI-compatible model to read project files and answer queries locally.
Provides web research through a local SearXNG search instance, with logging and LOCAL-mode query restrictions.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
NAVIGATOR
An independent MCP server for network-automation agents. It works with any MCP host (Hermes, OpenClaw, Claude, or your own agent): the agent gets one server, NAVIGATOR, that is its front door to inventories, credentials and devices. Inside it run three layers, and NAVIGATOR checks every call (project, mode, inventory, allowlist) before it reaches the layer below.
Layer | Component | Package | Status |
3 | NAVIGATOR: engineer and front door (projects, CLOUD / LOCAL, 9 roles incl. SHIP_ENGINEER, QC, lessons, scrambler, research, troubleshooting) |
| built (P7a, P7b, P7d), host setup in |
2 | RUDDER: every device: reads (any connection method, side by side, debug), changes approved out of band, scheduler |
| reads (P3, P5 delegated, P6 vManage), Arista (P4), Cisco and PAN-OS changes (P6), scheduled changes (P7b) |
1 | ATLAS: inventory, platform catalogue, encrypted credentials, interview, render, NetBox export |
| built (D1, P1, P2, render P7d) |
Services beside it: atlas-link (holds the key, decrypts one credential per connection) and rudder-scheduler.
atlas-mcp and rudder-mcp still run on their own for users who want only one layer; the default install is
the single navigator-mcp.

Documentation
Start with these five. Every other document is listed in docs/README.md, the one index.
docs/THREE_LAYERS.md: what the three layers are, in one page.
docs/INTEGRATION.md: connect a host (Hermes, OpenClaw, Claude Code, Cursor, your own…).
docs/INTERVIEW.md: first-time setup with
navigator-setup, and changing it later.docs/HOW_TO_USE.md: daily use on any host; projects; the CLOUD / LOCAL chat model.
docs/CHEATSHEET.md: what to say in chat and which tool it calls.
design/, decisions/ and labs/ hold the plans as written, every decision, and the test labs.
Models: NAVIGATOR has no model of its own. The host's chat model is CLOUD or LOCAL (on Hermes per
thread: /model cloud, /model local). LOCAL project data never goes to a cloud model; a local model
reads it through local_model (docs/LOCAL_MODELS.md).
Related MCP server: hpe-cx-mcp
NAVIGATOR tools (16; each takes an action)
No model inside: the host agent does the thinking. Everything ships in the package (roles, scrambler,
templates); EXTRA_SKILLS in navigator.yml only adds your own.
Tool | Actions | What it does |
| list, show, query, validate, history, platforms, platform, commands, template, render, netbox_export | ATLAS reads; |
| start, answer, status, preview, commit, cancel, list | the interview: draft → preview → the user's yes → commit |
| list, test | tags (never values); login test, optionally |
| read, facts, compare | allowlisted reads; |
| list, default | which adapter serves what; store a connection method as a default (an interview, versioned) |
| propose, schedule, status, apply, cancel, list | change tickets, approved only with |
| start, note, stop, show | a recorded session: every read in it goes to |
| create, show, list, status, close, task | project folders under WORKSPACE (TASK.md, RUNLOG.md, NAVIGATOR_STATE.json, LOGS/ CONFIG/ OUT/ RECORDS/ RAW/) |
| get, set | CLOUD or LOCAL. To LOCAL at once; to CLOUD only after |
| list, brief | the 9 roles (ANALYZER, CONFIG_GENERATOR, CONFIG_PUSHER, DATA_COLLECTOR, STATE_VALIDATOR, LOG_REVIEWER, DOCUMENTOR, SANITY_AGENT, SHIP_ENGINEER): a full brief for a subagent |
| check, record | SANITY_AGENT's 8-point checklist and verdict in the run log |
| add, list | lessons learned, append-only; LOCAL projects must be generic |
| list, load | shipped skills plus your own folders |
| sanitize, text, restore, map | the scrambler (below) |
| (query, fetch) | web search through the local SearXNG; LOCAL: generic queries only; always logged (docs/SEARXNG.md) |
| status, ask | a local OpenAI-compatible model (Ollama…) reads project files; LOCAL on a cloud host: the answer stays in |
The front-door check on every inventory, device, change and credential call: the project and its MODE (a
project with an inventory works only on it; a LOCAL project's data never reaches a cloud model; records go to <project>/RECORDS/DEVICES/ and a RUNLOG line),
the consumer's inventories and tags (ATLAS), the platform's command allowlist (in a lab inventory
LAB_ANY_SHOW can allow any plain show …), and writes only as tickets with /pushok.
The per-layer tables below describe the same functions as the standalone atlas-mcp / rudder-mcp tools.
Scrambler modes:
default: secrets only (passwords, type-7, enable secrets, TACACS/RADIUS keys, SNMP communities and v3 keys, routing auth keys, PSKs, hashes, certificates). Nothing else changes.
deep: default plus public IPs, public BGP ASNs, hostnames, domains, users, descriptions, serials, MACs and denylist terms, mapped per project and restorable.
level: strictalso maps object, ACL, VRF and policy names.
Every run is leak-checked; a failed run is written to SANITIZED/<ts>-<mode>-FAILED, and sanitize_text then returns no text. Maps are kept privately in ~/.navigator/scrambler/<project>/map.json (mode 600).
navigator-mcp # stdio; settings in navigator.yml (or NAVIGATOR_BOOTSTRAP)
navigator-skills export ~/.hermes/skills/navigator # roles + scrambler as SKILL.md folders for a hostATLAS tools (read-only; no tool ever returns a credential value)
Tool | What it does |
| inventories with device / controller / OOB counts and credential tags |
| one line per record, with filters (names, groups, FIELD=value, record_type) |
| chosen fields as structured data, plus PLATFORM, READS, WRITES, PRODUCTION |
| required fields, duplicates, secret-looking keys, catalogue checks, optional TCP probe |
| the platform catalogue: names per tool and which RUDDER adapter serves it |
| the read command allowlist per platform and category |
| tags, type, fields set or missing, encrypted or plain, which inventories use them |
| guided changes: draft → preview → the user's yes → commit with the preview's code |
| earlier versions of an inventory (restore with the |
| push an inventory to NetBox: dry run first, then commit with its code |
Making changes: the interview
Nothing is written until you have seen a preview and said yes. Every commit keeps the previous
version of each file and adds a line to ~/.atlas/audit.log. Hand-written inventories keep
their formatting: an added device appends only its own lines, and an edit changes only the edited keys.
Topic | Does |
| a new, empty inventory with default SITE / FAB / PRODUCTION |
| one device, controller or OOB record ( |
| many records from YAML or CSV, checked row by row |
| set FIELD=value on every record that matches (e.g. MATCH |
| go back to an earlier version (as a new version) |
| credential tags. Remove = disable, refused while in use |
| who may use which inventories and tags. Host only: an agent cannot widen its own access |
In a shell on the host (interactive; secrets are asked with getpass and encrypted at once):
atlas-interview run inventory_new
atlas-interview run record_add --inventory LAB2
atlas-interview run credential_new
atlas-interview run consumer_access --consumer LAB_BOT
atlas-interview list # open drafts (kept 7 days)
atlas-interview history LAB2 # versionsFrom an agent: interview_start → ask the user the returned questions → interview_answer →
interview_preview → show it → on the user's yes interview_commit(draft, code).
Passwords and keys are never asked in chat. The agent tells the user to run
atlas-interview secret <draft> LOGIN_PASSWORD on the host. Storing a credential needs the vault key
(atlas-vault init, then back the key up; see MIGRATION.md).
Not yet: hard deletes (they need the /pushok approver, P4), one-time secret links (P4), and the
setup topic (NAVIGATOR, P7).
NetBox export
# bootstrap.yml
NETBOX:
URL: https://netbox.example.net
TOKEN_CREDENTIAL: NETBOX_API # an API_TOKEN credential made with credential_new
VERIFY_TLS: truenetbox_export(name) lists what it would create or update (sites, manufacturers, device types,
roles, platforms, devices, a mgmt0 interface and the management IP as primary IP), with a code.
netbox_export(name, code) applies exactly that plan. It only updates devices it created (tag
atlas) and never deletes. Enabled DEVICE records only for now.
Inventory files (INVENTORY_<NAME>.yml in DATA_PATH) hold INVENTORY: (devices), CONTROLLERS: and OOB: lists.
RUDDER P6: Cisco and PAN-OS changes, Viptela reads
Platform | Lines | Dry run | Apply / rollback |
Cisco IOS / IOS-XE / NX-OS (SSH) | as in | computed from the running config ( | checkpoint ( |
PAN-OS (SSH + XML API) |
| lines into the candidate, | saved |
Viptela (SD-WAN Manager API) | reads only | – | – |
rudder.yml: API_VERIFY_TLS (vManage, PAN-OS API), COMMIT_WAIT (seconds for a PAN-OS commit). One ticket holds one kind of device. IOS-XR changes are not built yet.
RUDDER delegated adapters (P5): existing MCP servers behind the same front door
For platforms an existing open-source MCP server already serves well, RUDDER is an MCP client of that server. Each call:
starts the server as a child process;
writes that server's inventory or testbed into a private temp folder (references only, no passwords);
passes the credential from ATLAS only in the child's environment, which is otherwise minimal;
calls the tool, then stops the server and removes the folder.
The command allowlist still applies first, and results come back in RUDDER's normal record format.
Server | Used for | Tool | Notes |
pyATS (upstream pyATS MCP) | Cisco IOS / IOS-XE / NX-OS / IOS-XR / ASA reads |
| Genie-parsed JSON where a parser exists. HTTP-only upstream: bound to 127.0.0.1 on a free port for one call, then stopped |
multivendor-cli-mcp | SR Linux, SR OS, VyOS, RouterOS, SONiC, OS10, EXOS, VRP, EdgeOS, Cumulus, FRR reads |
| stdio; read-only (writes not enabled) |
fortinet-mcp | FortiGate reads |
| API_TOKEN credential; the "commands" in COMMANDS.yml are these tool names |
scripts/install_delegated.sh # ~/.rudder/delegated: src/ (pinned server sources), pyATS_MCP, one venv each
# SERVERS_REPO / SERVERS_REF / PYATS_MCP_REPO choose where they come fromWrites through these servers (multivendor apply_config, FortiManager install) will go through RUDDER's change
tickets and /pushok. They are not enabled yet.
RUDDER changes (P4): propose → /pushok out of band → apply
The whole change path, its safety checks and what is planned: docs/RUDDER.md.
Tool | What it does |
| check lines (deny list), refuse PRODUCTION, lock devices, save the baseline, dry-run diff on the device, send the approval request (code only to the human's Telegram) |
| waiting_approval / approved / applied / failed / rejected / expired / cancelled, diff per device, next step |
| only after |
| release locks and void the approval / recent tickets |
| apply at a set time: approved in advance, 30 s notice with a stop code, applied by |
There is no approve tool. With the Hermes approval channel, hermes -p <approver profile> send delivers
the request to a separate bot, and the push-approve plugin turns /pushok CODE into a decision file.
RUDDER keeps only hashes of the code, and an approval works once.
Settings are in rudder.yml (APPROVAL, COMMIT_TIMER, ALLOW_PRODUCTION, DENY_LINES).
Arista over eAPI uses configuration sessions:
Dry run: a session, its diff, then abort.
Apply:
commit timer, so the switch rolls back by itself if RUDDER dies.Verify: the same lines must now change nothing, and the optional verify commands must match.
Finish:
configure session … committo keep it, or… abortto roll back.
RUDDER tools (layer 2, reads)
Tool | What it does |
| run allowlisted commands (a category or exact commands) on devices chosen from an ATLAS inventory; every output saved to |
| the same reads on one device through two or more connection methods, with timing, errors and a diff |
| connect and run |
| hostname, model, version, serial, MAC, uptime (Arista EOS) |
| which adapter serves each platform and what works in this build |
Adapters in P3:
Arista EOS over eAPI: JSON, with text for commands that have no JSON form.
Arista EOS over SSH with
| json, so the output matches eAPI.Generic netmiko text reads for any platform with a command list, for example PAN-OS over SSH.
Platforms served by a delegated MCP server report "P5"; vManage reports "P6".
RUDDER never reads ATLAS's files. It asks ATLAS over the ATLAS link, a Unix socket (mode 600) with a token per client:
atlas-link token RUDDER # once: creates ~/.config/rudder/atlas-link.token (mode 600)
atlas-link serve # keep running: install scripts/atlas-link.service (docs/ATLAS.md)
rudder-mcp # the RUDDER MCP server (stdio); settings in rudder.ymlAdd ~/.config/rudder/ and ~/.rudder/ to the host's deny rules as well.
Install
cd ~/navigator
python3 -m venv .venv
.venv/bin/pip install setuptools wheel
.venv/bin/pip install --no-build-isolation -e ".[test]"Then edit bootstrap.yml (DATA_PATH, KEY_FILE, CONSUMER), or point ATLAS_BOOTSTRAP at your own copy.
Hermes (~/.hermes/config.yaml or the profile's, stdio): one entry, the front door.
mcp_servers:
navigator:
command: /home/<user>/navigator/.venv/bin/navigator-mcp
env: {NAVIGATOR_BOOTSTRAP: /home/<user>/.config/navigator/navigator.yml}(atlas-mcp / rudder-mcp entries are only for hosts that want one layer on its own; an agent that has
navigator should not also have them, or it could skip the front-door check.)
OpenClaw (HTTPS): run atlas-mcp --serve (systemd atlas-mcp-https, port 8792, TLS and logins built in, docs/HTTPS.md), and add it to mcp.servers in openclaw.json with ATLAS_CONSUMER set to that agent's consumer name (e.g. LAB_BOT).
Add the key folder (~/.config/atlas/), DATA_PATH and STATE_PATH (~/.atlas/) to the host's deny rules: agents use the tools, never the files.
Host settings: navigator-setup
Run once after install, and again whenever something changes (host shell only, never a chat tool):
navigator-setup # the interview: PROJECT_ROOT, SKILLS_ROOT, approvals, retention, MODELS, HTTPS
navigator-setup show
navigator-setup set APPROVAL.WEB_BIND <host-lan-address>:8790
navigator-setup set MODELS.LOCAL_URL http://127.0.0.1:11434/v1 MODELS.LOCAL_MODEL qwen3.5:9bDetails: docs/INTERVIEW.md, docs/APPROVALS.md, docs/LOCAL_MODELS.md.
Services and ports
What | Runs as | Listens on | Open in the firewall? |
| started by the MCP host (stdio) | nothing | no |
| systemd user services | TCP 8791 / 8792 / 8793, TLS + login | yes, for the ones you use, from the clients' networks |
| systemd user service | a Unix socket, | no |
| systemd user service | nothing, unless change pages are on | no |
change pages (read-only page per ticket, linked from the approval message) | inside | TCP 8790 on the address in | yes: TCP 8790 from the networks the approvers use |
SearXNG (web search for | Docker | 127.0.0.1:8888 | no |
delegated pyATS MCP | started by RUDDER per call | 127.0.0.1, a free port, only during the call | no |
The change pages are served directly by rudder-scheduler (Python's standard HTTP server): no nginx or
other reverse proxy, nothing else to install. HTTPS with NAVIGATOR's local CA once navigator-setup tls init
has run (APPROVAL.WEB_TLS auto; docs/HTTPS.md), meant for the LAN, for example with ufw:
sudo ufw allow from <lan-cidr> to any port 8790 proto tcp comment 'RUDDER change pages'To reach the pages from outside later, use a VPN (the links then use its name: navigator-setup set APPROVAL.WEB_URL https://<vpn-name>:8790) rather than opening the port to the internet. Without
APPROVAL.WEB_BIND nothing listens and the approval message carries the diff itself.
Credentials
atlas-vault status | init | encrypt | check | rekey. Read MIGRATION.md before encrypting a real file.
Tests
.venv/bin/python -m pytest -q # no devices, no network
.venv/bin/python tests/smoke_stdio.py # real DATA_PATH over stdio; prints summaries only
python scripts/gen_platforms.py --check # with netmiko installed: is PLATFORMS.yml current?Platform catalogue
atlas_inventory/catalog/PLATFORMS.yml is generated from netmiko's platform list plus platforms_overlay.yml (hand-kept: vendor, aliases, tool names, adapters). Edit the overlay, then run python scripts/gen_platforms.py. COMMANDS.yml is the read command allowlist.
License
Apache License 2.0. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed access to sensitive data, secrets and APIs for AI agents. A signed proof for each decision.
Your agents' cloud for individuals and teams. Search, execute, packages, jobs, and credentials.
Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key
Connect, monitor, and control AI agents — tasks, approvals, schedules, and governance.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI assistants with direct access to multi-vendor network devices for tasks like configuration management, health checks, and topology discovery through 35 specialized tools. It enables natural language control over platforms including Cisco, Juniper, and Nokia using SSH, NETCONF, and SNMP protocols.12MIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP-capable AI agents to observe, troubleshoot, and configure Aruba CX (AOS-CX) switches through REST and SSH, with safety controls, inventory management, and verification workflows.-
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to safely troubleshoot networks through read-only tools for device inventory, interface status, VLAN paths, BGP neighbors, route lookups, and interface error detection. Integrates with Microsoft Copilot Studio and Teams for natural-language-driven network diagnostics.-
- AlicenseNot gradedqualityAmaintenanceEnables secure network diagnostics and approved changes on network devices via SSH, with alias-based access and credential injection.2MIT