casper-network-mcp
This MCP server provides a search-and-invoke gateway to thousands of network-management API operations plus read-only diagnostics and guarded changes across supported HPE Aruba/Juniper products.
Discover tools:
find_toolmaps plain-language tasks or exact API calls to the right tool, optionally filtered by product and with schemas.Run safe reads/checks:
invoke_read_toolexecutes read-only or non-disruptive troubleshooting tools and refuses state-changing tools.Run changes with approval:
invoke_toolcan run any tool, including config, disruptive, firmware, delete, or admin actions; Casper prompts before changes and--read-onlyblocks writes.Aggregate results:
invoke_read_toolsupports cursors,all_pages,fields, andgroup_byfor site-wide pagination, filtering, and grouping in one call.Check access:
access_checkreports per-product login status, permissions, named Central logins, and whether the server is read-only.Use product-specific capabilities: Central, Mist, ClearPass, UXI, OpsRamp, and AOS 8 tools; overviews; ClearPass Access Tracker and denial diagnostics; AOS 8 read-only client/auth/show commands; device config-management checks; busy-hours analysis; and offline API document lookup.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@casper-network-mcp show me the top alarms on my Aruba Central site right now"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
casper-network-mcp
One small MCP server for HPE Aruba Networking Central, Juniper Mist and HPE Aruba Networking ClearPass, built for Casper. Your AI sees four tools; behind them are about 3,900 tools for the three products, each one labelled with the kind of change it makes.
You normally never install this yourself: Casper sets it up, pins the exact version and starts it for you.
What it does
Tool | What it is for |
| Finds the right tool for what you asked ("bounce port 7 on the closet switch") and says what kind of change it makes: read, troubleshoot, config, disruptive, firmware, delete or admin. |
| Runs a tool that only reads, or a non-disruptive troubleshooting check (ping, show). Anything else is refused. Show-only checks are labelled |
| Runs any tool, including ones that change your network. Casper asks you first. |
| Says, for each product, whether a login is set and where that login can change things. |
Behind them:
hand-written tools for everyday work (sites, clients, alarms, switch ports, guests, sessions, SSIDs, VLANs and more), each one checked against the vendor's own API description;
one generated tool for every operation in the bundled API descriptions;
overview tools for broad questions:
central_site_overview,mist_site_overviewandclearpass_overviewgive health, device counts and the top alarms in one read;clearpass_why_deniedsummarizes recent sessions, endpoint status/profile, NAD and applied roles for exactly one MAC or username. The bundled 6.12.7 API exposes active accounting sessions, not full Access Tracker rejects; without the Access Tracker database login, missing auth results, reject reasons and enforcement profiles remain unknown. With it, the latest Access Tracker records are added;clearpass_access_trackerreads Access Tracker itself for one MAC or username: accept or reject, the error code and its text (206 Access denied by policy, 215 TLS session error), alerts, auth type, roles, enforcement profiles and NAD, newest first, over the lasthours(1-720, default 24) with up tolimitrecords (1-100, default 10). No ClearPass API has Access Tracker, so it reads ClearPass's own database as its read-onlyappexternaluser (see Logins); it only ever runs fixedSELECTs;AOS 8 (ArubaOS 8 Mobility Conductor or Mobility Controller), read only:
aos8_find_client(MAC, IP or username),aos8_get_client_detail(role and how it was derived, VLAN, auth method and RADIUS server),aos8_get_client_history,aos8_auth_trace(the controller's 802.1X / RADIUS trace for one MAC: rejects, timeouts),aos8_list_aaa_profilesandaos8_list_aaa_servers(which RADIUS servers, often ClearPass, a profile uses), user roles, a short list of auth config objects, andaos8_show_command, which runs only allow-listedshowcommands;ClearPass session and auth-failure reads accept MAC, username, NAD IP, accounting service type and ISO 8601 start/end times (with timezone). Time windows scan at most ten pages locally;
next_server_offsetcontinues a scan, including an empty page. The service filter is not an Access Tracker policy service name;lookup_api, which answers exact questions about the vendors' APIs (endpoints, fields, allowed values) from the bundled documents, with no network.get_device_config_managementsays in one read whether new Central manages a device's configuration (a device group, config health tracking it) or not; inventory labels such as provisioned, device function and site are not proof, and the answer shows which evidence it used;busy_hoursprofiles a site hour by hour over up to a month (client counts, or a switch uplink's traffic) in your time zone and names the quietest window for planned downtime.
Related MCP server: HPE Aruba Networking Central MCP Server
Site-wide answers in one call
invoke_read_tool can shape a reply before it reaches the AI, so a question about every AP or every client is one
call, not a page loop:
Option | What it does |
| Follows the tool's own paging ( |
| Keeps only these keys of each item; |
| Returns a count per value of one field instead of the items. |
For example {"name": "central_get_device_inventory_v1", "arguments": {}, "all_pages": true, "group_by": "status"}
answers "how many devices are in each state" for a whole account. Shaping is for reads only,
so a repeated call never repeats a change.
Running it
uvx --from casper-network-mcp==0.1.7 casper-network-mcp --read-onlyOption | Meaning |
| Only read and run checks; never send a change. Read once at start: nothing turns writes on while it runs. Casper passes this until you allow changes. |
| The default: talk over standard input and output. |
| Listen on this machine only ( |
From a checkout, .mcp.json.example starts it read-only with uv run; logins come from your shell.
Logins
The server reads only these variables from the environment Casper starts it with. It reads no settings files.
Leave out a product you do not use: the server still starts, access_check says that login is missing, and a call
to one of its tools answers {"error": "login_missing", "product": "..."}.
Product | Variables |
Juniper Mist |
|
HPE Aruba Networking Central |
|
HPE Aruba Networking ClearPass |
|
ClearPass Access Tracker (optional) |
|
HPE Aruba Networking UXI |
|
AOS 8 (Mobility Conductor or Controller) |
|
HPE OpsRamp |
|
For ClearPass, an API client is best: the server logs in with it and gets a new token before the old one runs out.
In ClearPass Guest, open Administration > API Services > API Clients, create a client with grant type Client
Credentials and an operator profile that allows what you want Casper to do, and set its client ID and secret. If
CLEARPASS_API_TOKEN is set it is used as is and the client ID and secret are ignored.
Access Tracker is not in any ClearPass API, so clearpass_access_tracker reads it from ClearPass's database as
appexternal, ClearPass's built-in read-only database user. Set its password in ClearPass under Administration >
Server Manager > Server Configuration > Change Password (user appexternal) and put the same value in
CLEARPASS_DB_PASSWORD. Records come from the logs database (tipsLogDb, port 5433) and error-code text from the
config database (tipsdb, port 5432); both ports must be reachable from where the server runs. If the error-code
text can't be read, records keep the numeric code. Each call opens its own connections and closes them, marks the
session read-only and stops any query after 15 seconds. TLS is tried first; only a server that refuses TLS is read
over a plain connection, and the reply's transport says which. ClearPass's database certificate is its own, so
it is not checked. Without the password the tool answers login_missing with what to set, and access_check
reports ClearPass's access_tracker as missing.
For AOS 8 the server logs in to the controller's REST API (POST /v1/api/login), keeps the session id
(UIDARUBA) and its cookie in memory, reuses that one session (controllers allow only a few), logs in again once
when the controller answers 401, and logs out (GET /v1/api/logout) when it stops. The session id, the cookie and
the password never appear in a reply or an error. Point AOS8_BASE_URL at the Mobility Conductor or straight at a
managed controller; a Conductor holds no clients itself, so client searches fall back to its global user table.
The controller's certificate is checked like every other product's: a self-signed or private-CA certificate needs
that CA trusted, for example with SSL_CERT_FILE. access_check reports AOS 8 as unknown (the API has no call
that says what a login may change) after one show version, with reads: ok, or login: expired when the login
is turned away.
A second Central account (a customer's temporary key, a lab) needs no second server. Set
CENTRAL_TEMP_BASE_URL, CENTRAL_TEMP_CLIENT_ID and CENTRAL_TEMP_CLIENT_SECRET and the login is called temp.
access_check lists it under Central's named_logins, and invoke_read_tool or invoke_tool with "login": "temp" runs that one call as it; without login the main account answers. Names are letters and digits. The
--read-only pin covers every login. Remove the variables when the key is retired.
A Central login here is a GreenLake API client, so it reaches new Central only: Classic Central's API
(apigw-*.central.arubanetworks.com) does not accept GreenLake tokens, and access_check says so.
ClearPass API tokens expire (the API client's token lifetime in ClearPass sets when); a pasted token is not renewed.
When a product turns a login away (HTTP 401), access_check reports that product with "login": "expired" and a
call to one of its tools returns {"error": "login_expired", "product": ...}, so the client can ask you for a new one.
Changes to your network
There are no write switches. What a login may do is set by its role in the product, and Casper asks you before every change, showing the tool and what it changes. On top of that:
--read-onlyrefuses every change before anything is sent;a path piece that could reach somewhere else (
/,?,#,..) is refused before anything is sent;when the server knows a Mist login can only read a site, a change to that site is refused before anything is sent;
tools that disrupt the network (cable tests, reboots, port and PoE bounces, disconnects) require
invoke_tooland are labelled disruptive, so Casper asks every time;show-only checks (LLDP neighbours, ARP and MAC tables, port counters, spanning tree,
cx_showand the other show tools, which refuse anything but one-lineshowcommands) are reads: kindtroubleshoot, labelread, no box in Casper. Ping, traceroute and other checks that send traffic from the device keep thediagnosticlabel, so Casper still asks;tokens, passwords and pre-shared keys are hidden in replies and errors (AOS 8 session ids and cookies too);
AOS 8 is read only: every tool sends
GET;aos8_show_commandrefuses anything that is not one allow-listedshowcommand (no;,|or new lines, nothing that shows the running config or a secret);the ClearPass Access Tracker database is only read: fixed
SELECTs with every value passed as a parameter, as the read-onlyappexternaluser, in a read-only session.
The server never asks you to type anything and never treats an argument the AI sets as your approval. Approval is Casper's box only.
Compact Mist discovery diagnostics
For AirPrint, Bonjour or mDNS problems, find mist_wlan_discovery_summary with
find_tool("AirPrint discovery", product="mist", include_schema=True), then call it with
{"ssid": "Example"}. Add site_id or org_id when known to skip scope lookups.
It returns exact SSID matches, VLAN, isolation, mDNS/SSDP filtering and Bonjour service evidence,
including template-derived WLANs, without dumping clients or full site settings. The same evidence helps
investigate Sonos and AirPlay discovery, but does not verify playback or cross-VLAN reachability.
Automatic scope discovery is limited to 10 sites (at most four concurrent WLAN reads).
Multiple orgs, larger scopes and duplicate SSIDs require explicit target selection;
incomplete reads are reported, never treated as a healthy network or an absent SSID.
This tool only reads: findings do not confirm printer reachability or trigger a change.
mist_list_wlans also includes discovery settings so a separate full WLAN read is often unnecessary.
See implementation and validation notes for usage, limitations, the two-MCP-call offline regression scenario and Sonos/AirPlay follow-up evidence.
Failures and recovery
API failures keep their existing error, status, detail, request_id and url fields, and add
code and guidance: permission_denied for 403, rate_limited for 429, upstream_error for 5xx,
and api_error otherwise. A valid Retry-After header also supplies retry_after_seconds.
The existing login_missing and login_expired replies are unchanged.
Transport failures report timeout or connection_error. After a write timeout, the outcome is unknown:
check the target's current state before retrying. Writes are never resent automatically, including after
401; renewable logins refresh and resend only plain reads.
How well find_tool finds tools
find_tool was measured on a fixed set of 60 plain questions (20 each for Central, Mist and ClearPass, in
tests/bench/find_tool_questions.yaml), then tuned one change at a time. A change stayed only if it found more
right tools in the top 3, or answered faster without finding fewer. Run uv run python scripts/bench_find_tool.py
to measure it yourself.
Right tool first | Right tool in top 3 | Top 3, no product given | Time per question (p50 / p95) | First question in a new process | |
Before | 67% | 77% | 68% | 0.6 / 1.6 ms | 3.4 s |
After | 85% | 100% | 90% | 0.6 / 2.0 ms | 0.4 s |
What changed, in order:
Synonyms (
router/synonyms.yaml) and plural folding: "access point" findsap, "kick" finds disconnect, "who is on" finds clients. Top 3: 77% to 97%.Ranking by what the question asks: "what" and "show" prefer tools that read, "create", "delete" and "change" prefer those changes; the product name in a tool's name no longer counts against it. Top 3: 97% to 98%, first pick 75% to 87%. (Weighting name words over description words was tried and dropped: top 3 fell to 90-95%.)
A prebuilt word index shipped in the package (
router/index.json): the first question no longer loads every tool. First question: 3.4 s to 0.4 s.Overview tools for broad questions (
central_site_overview,mist_site_overview,clearpass_overview: health, device counts and top alarms in one read) andmist_list_site_clientsfor "who is on the wifi". A synonym that spreads into several words ("wifi" to wlan, ssid, wireless) now counts once. Top 3: 98% to 100%.
Times are on a laptop with the router already loaded, except the last column.
First-pick follow-up
A later offline comparison uses merged PR #12 (72e41ce) as its baseline. The original
75-question held-out dataset was unavailable; these are 36 new synthetic evaluation questions
(12 per product), frozen before router edits. Only aggregate evaluation baseline scores were inspected
before tuning; evaluation misses were not used. This small sample is not evidence of equivalent gains
on real requests or on the original 75 questions.
The additional 30-question development set exposed a general parsing error: a leading product name
or alias hid the following action verb. find_tool now skips those prefixes when reading intent.
Scoring weights, candidate retrieval, tool summaries, the shipped index and dependencies are unchanged.
Product | First, filtered | Top 3, filtered | First, unfiltered | Top 3, unfiltered | MRR, filtered |
Central | 10/12 → 12/12 | 11/12 → 12/12 | 10/12 → 12/12 | 11/12 → 12/12 | 0.8869 → 1.0000 |
Mist | 10/12 → 11/12 | 12/12 → 12/12 | 9/12 → 10/12 | 12/12 → 12/12 | 0.9167 → 0.9583 |
ClearPass | 10/12 → 11/12 | 12/12 → 12/12 | 10/12 → 11/12 | 12/12 → 12/12 | 0.9028 → 0.9583 |
Top-ten accuracy remains 12/12 for every product in both modes. Warm filtered top-three p50/p95 was 0.72/5.37 ms before and 0.80/5.95 ms after in this local measurement, below the unchanged 50 ms p95 limit. The original 60-question benchmark's per-product accuracy is unchanged in both modes; its p50/p95 was 0.51/2.27 ms before and 0.53/2.29 ms after. Timings are descriptive, not portable speed guarantees.
Two filtered evaluation first-pick failures remain: "show WLAN security for one WLAN" and
"show every authentication service"; each acceptable answer is second. Unfiltered evaluation also
prefers Central's overview for "show the site health overview". No further tuning used these misses.
The new development set also exposes a limitation: without a product filter, "mist restart an access point"
drops out of the top three (Mist unfiltered development top-three: 11/11 → 10/11). These measurements
predate the product-routing fix: an unambiguous product name or alias now restricts plain-language results
to that product when no explicit filter is supplied. Explicit filters and exact API matches take precedence;
requests naming several products remain unfiltered.
The benchmark now reports every wrong-first result with its expected rank, separately from top-three misses, plus per-product filtered/unfiltered top-one, top-three, top-ten and MRR:
uv run python scripts/bench_find_tool.py --questions tests/bench/find_tool_evaluation.yaml
uv run python scripts/bench_find_tool.py --questions tests/bench/find_tool_evaluation.yaml --jsonDataset provenance, development failure categories and frozen baseline hashes are in
tests/bench/README.md. This evaluation set is now regression data; another
tuning cycle needs a fresh evaluation set. Tests guard each product's first/top-three scores independently,
so improvements elsewhere cannot conceal regressions.
What is in the package
The package includes HPE's proprietary API documents (not MIT; see specs/NOTICE.md) and Juniper Mist's MIT
OpenAPI file. They are stored exactly as the vendors serve them; scripts/refresh_specs.py --check fetches them
again and confirms every hash. See NOTICE.md and THIRD_PARTY_NOTICES.md.
The package has no install step, downloads nothing when it starts and never updates itself.
Agent skill
skills/device-troubleshoot/SKILL.md is an agent skill for asking about one device or user ("why can't this MAC
connect?"). It checks Mist, Central or AOS 8 first, then ClearPass, using only this server's read tools, and answers with
a timeline and root cause. Copy the folder into your agent's skills directory (for example ~/.agents/skills/).
It is not part of the Python package.
Working on it
uv sync
uv run pytest -q
uv run ruff check .
uv run python scripts/bench_find_tool.py # find_tool accuracy and speed
uv run python scripts/build_manifests.py # after the bundled specs change
uv run python scripts/build_index.py # after any tool changesA release is built from a v* tag: the wheel, then casper-network-mcp.lock.txt (every dependency pinned by hash,
plus this package pinned to the wheel's own hash, made by scripts/make_lock.py). The release checks that lock
installs with Casper's exact command before publishing:
uv pip install --require-hashes --no-deps --only-binary :all: -r casper-network-mcp.lock.txtSecurity
Report problems privately; see SECURITY.md.
Licence
MIT for this project's code (LICENSE). The bundled vendor documents keep their own terms (NOTICE.md).
Available Tools
4 toolsaccess_checkBRead-onlyIdempotent
What each product login can do, and whether this server is read-only.
Inputs: no named parameters. Returns: object
find_toolARead-onlyIdempotent
Find the tool for a task. Call this first.
query: what you want to do, in plain words ("bounce port 7 on the
closet switch") or an exact API call ("GET /api/v1/sites/{site_id}").
product: central, mist, clearpass, uxi, opsramp or specs (the API document lookup).
Each hit has name, product, summary, kind (read, troubleshoot, config,
disruptive, firmware, delete or admin) and label (read, diagnostic, write
or destructive; a show-only check is troubleshoot with label read). Pass include_schema
to get the arguments a tool takes. Then call invoke_read_tool (kind
read or troubleshoot) or invoke_tool.
Inputs: query (required), top_k, product, include_schema. Returns: result
invoke_read_toolARead-onlyIdempotent
Run a tool that only reads, or a non-disruptive troubleshooting check (ping, show). Names come from find_tool.
Cable tests can interrupt a link and require invoke_tool.
A tool that can change something is refused with "not_a_read_tool".
cursor: the next_cursor from a reply that was cut short, to get the rest.
login: a named Central login from access_check (default: the main one).
all_pages: fetch every page of a list here (up to 50 pages / 10,000 items) instead of one.
fields: keep only these keys of each item ("radio.channel" reaches inside); cuts big replies.
group_by: return a count per value of this field instead of the items ("firmwareVersion").
Together they answer site-wide questions in one call: all_pages + group_by="status".
Inputs: name (required), login, cursor, fields, +3 more.
invoke_toolB
Run any tool from find_tool, including ones that change the network.
The tool's own kind (from find_tool) says what it changes.
login: a named Central login from access_check (default: the main one).
Inputs: name (required), login, arguments.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The workflow is clearly staged: find_tool discovers, access_check reports permissions, and the two invoke tools execute. The only fuzzy boundary is invoke_read_tool vs invoke_tool, since invoke_tool claims to run 'any tool from find_tool', including reads, but the read variant's extra pagination/field/group_by options make the intended split understandable.
All names are snake_case and readable, with two clear verb_verb_noun pairs (invoke_read_tool, invoke_tool) and find_tool. access_check breaks the verb_noun pattern by being noun-first, a minor deviation rather than a real inconsistency.
Four tools is a sensible fixed facade for a gateway that multiplexes six products via dynamic discovery. There is slight redundancy in having invoke_tool capable of doing everything invoke_read_tool does, but the extra read-only conveniences justify keeping both.
Discovery, permission inspection, schema retrieval (include_schema), pagination, and both safe and destructive execution are all covered, which is solid for a meta-server. Gaps are minor: there is no way to enumerate all available tools or list by product without a free-text query, and no login/credential management beyond naming a login.
Maintenance
Related MCP Connectors
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Search 16,000+ API operations and 95 built tools by need, then call any of them by name
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
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 gradedqualityDmaintenanceExposes 90 production-grade tools for interacting with the complete HPE Aruba Networking Central REST API surface, including network inventory, configuration, and security management. It features enterprise-ready OAuth2 handling and semantic tool filtering for optimized performance with both hosted and local LLMs.-
- AlicenseAqualityAmaintenanceEnables conversational automation of HPE Aruba Central network operations through Claude Code. Provides 88 tools across monitoring, configuration, and operations domains for device migration, SSID management, switch provisioning, and GreenLake Platform integration.162MIT
- 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.-