Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

Horizon Fidelity Monitor

by leocelisversion 0.3.2i★ 0iRuns in the cloudOfficial site ↗
Registry nameio.github.leocelis/horizon-fidelity-monitor

How to install

What it does

Real-time conversation health for AI agents: drift, desync, causal collapse, plus mission clocks.

  • Connects Runs in the cloud
  • Account or key Needs Authorization
  • Category Clinics & health

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity0/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering8/8The cloud endpoint answered at the last check
Usage score20/100

Quality: Passed 3/5 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Horizon Fidelity Monitor. Follow https://mcp.popnx.com/i/leocelis-horizon-fidelity-monitor.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/5 checks · What you ask goes through the maker’s server (horizon.leocelis.com) · ✓ Commands checked Nov 20, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude · about 5 min

You need a Horizon Fidelity Monitor key (create it on the maker’s site) · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it

  1. Sign up and create a Horizon Fidelity Monitor key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the Horizon Fidelity Monitor site ↗

  2. Open Claude’s Connectors page

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  3. Click “Add” → “Custom” → “Web” and fill in these 2 fields

    Copy each value into the field with the same name in Claude, then click Continue

    Name · NameHorizon Fidelity Monitor
    Remote MCP server URL · Addresshttps://horizon.leocelis.com/sse

    Under Request headers, add this name and value

    Header nameAuthorization
    ValueBearer <paste your key here>

    Paste the key only into the app’s field, never into a chat or to anyone

    Click Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add

  4. Turn it on in a chat

    +ConnectorsHorizon Fidelity Monitor

  5. Try it

    Use Horizon Fidelity Monitor and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Horizon Fidelity Monitor or shows a Horizon Fidelity Monitor tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Horizon Fidelity Monitor yet

Horizon Fidelity Monitor needs your own key to connect, but OpenAI’s help page only describes OAuth sign-in; there is no key option we could verify

What you can do instead

A · Use an app that can connect Horizon Fidelity Monitor

  • You need a Horizon Fidelity Monitor key (create it on the maker’s site) · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
  • You need a Horizon Fidelity Monitor key (create it on the maker’s site)
  • You need a Horizon Fidelity Monitor key (create it on the maker’s site)
  • You need a Horizon Fidelity Monitor key (create it on the maker’s site)

B · Others in Clinics & health that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code · about 5 min

You need a Horizon Fidelity Monitor key (create it on the maker’s site)

  1. Sign up and create a Horizon Fidelity Monitor key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the Horizon Fidelity Monitor site ↗

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --transport sse --scope user horizon-fidelity-monitor https://horizon.leocelis.com/sse --header 'Authorization: Bearer {api_key}'

    Replace “your-value” with your key before pressing Enter

    Paste the key only into the app’s field, never into a chat or to anyone

  4. Type /mcp in Claude Code

    You should see Horizon Fidelity Monitor listed as connected

  5. Try it

    Use Horizon Fidelity Monitor and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Horizon Fidelity Monitor or shows a Horizon Fidelity Monitor tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor · about 5 min

You need a Horizon Fidelity Monitor key (create it on the maker’s site)

  1. Sign up and create a Horizon Fidelity Monitor key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the Horizon Fidelity Monitor site ↗

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Fill in your key

    In the Horizon Fidelity Monitor settings, Authorization is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  4. Open the AI chat in Cursor in Agent mode

  5. Try it

    Use Horizon Fidelity Monitor and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Horizon Fidelity Monitor or shows a Horizon Fidelity Monitor tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code · about 5 min

You need a Horizon Fidelity Monitor key (create it on the maker’s site)

  1. Sign up and create a Horizon Fidelity Monitor key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the Horizon Fidelity Monitor site ↗

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Fill in your key

    In the Horizon Fidelity Monitor settings, Authorization is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  4. Open the AI chat in VS Code in Agent mode

  5. Try it

    Use Horizon Fidelity Monitor and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Horizon Fidelity Monitor or shows a Horizon Fidelity Monitor tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

Address for apps that connect over the web

Addresshttps://horizon.leocelis.com/sse

JSON settings are under “For developers” below

Stuck? Ask people who use Horizon Fidelity Monitor💬 Discussion →
For developers: Terminal commands and JSON settings

Over the web

Claude Code

claude mcp add --transport sse --scope user horizon-fidelity-monitor https://horizon.leocelis.com/sse --header 'Authorization: Bearer {api_key}'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "horizon-fidelity-monitor": {
      "url": "https://horizon.leocelis.com/sse",
      "headers": {
        "Authorization": "Bearer {api_key}"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "horizon-fidelity-monitor": {
      "type": "sse",
      "url": "https://horizon.leocelis.com/sse",
      "headers": {
        "Authorization": "Bearer {api_key}"
      }
    }
  }
}

Values you fill in

  • Authorization secret required HTTP header
    API key for the Horizon hosted server. Request one at https://github.com/leocelis/horizon/discussions

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
Not on npm/PyPI
Connection
Runs in the cloud
Latest versioni
0.3.2
Published to registryi
Nov 8, 2026
Code last changedi
Nov 17, 2026
Last checked
Nov 20, 2026
Maker
leocelis
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Connect over the internet in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

All apps, with pros and cons →

Related guides

What it can do

The server asks you to sign in before it lists its tools.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 20, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account leocelis, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 3 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • ! Caution

    Endpoint responds

    Refused access (HTTP 401) without offering OAuth sign-in. It may need a key, or it may be blocking bots; not confirmed.

  • ! Caution

    Sign-in with OAuth

    Needs a key or token that you copy and paste yourself

  • … Not checked yet

    No hidden instructions in tool descriptions

    Not checked yet; we read the tool list when we check the endpoint

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/leocelis-horizon-fidelity-monitor.svg)](https://mcp.popnx.com/en/servers/leocelis-horizon-fidelity-monitor)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Clinics & healthi

  • More stars than 0% of the other 1199 servers in this category
  • Published to the registry more recently than 73% of the other 1199 servers in this category
  • Basic checks equal to or better than 12% of the other 1199 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Horizon Fidelity Monitor safe?

It passed 3 of 5 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: Authorization

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed 3 days ago, and the latest version (0.3.2) reached the registry 12 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).

What can I use instead?

In the same category: Medplum MCP, Mirobody, Codescene MCP Server, Marrow, WHOOP — MissingMCP

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Medplum MCP

Securely access and manage FHIR healthcare data stored in Medplum.

by medplumWidely used★ 2.8KUpdated 4 months ago

Runs in the cloud✓ service owner · medplum.com

Mirobody

Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.

by thetahealthGrowing↓ 725/wk★ 1.6KUpdated yesterday

Runs on your computer✓ thetahealth.ai

Codescene MCP Server

An MCP server that provides CodeScene Code Health analysis tools.

by codescene-ossGrowing↓ 3.8K/wk★ 85Updated 8 months ago

Runs on your computer✓ service owner · codescene.com

Marrow

Marrow Health: your Apple Health data over MCP, from the free iOS app. Reads, and writes on demand.

by skeletonarmytechEarly↓ 62/wk★ 5Updated 29 days ago

Runs on your computer✓ skeletonarmy.tech
Compared with similar ones
This one
Horizon Fidelity Monitor
Medplum MCPMirobodyCodescene MCP ServerMarrowWHOOP — MissingMCP
Runs whereRuns in the cloud, nothing to installRuns in the cloud, nothing to installInstalls on your computerInstalls on your computerInstalls on your computerRuns in the cloud, nothing to install
Needs a keyYesNoNoNoNoNo
Add with + in ClaudeNoNoNoNoNoNo
Basic checks3/54/43/32/33/32/4
LicenseMITApache-2.0Apache-2.0NOASSERTIONMITMIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Horizon Fidelity Monitor

"Quality is not a model property — it is a conversation property."

Horizon is a real-time conversation health monitor for AI agents. It tracks the structural dynamics of multi-turn conversations — semantic drift, information gain, ontological gap width, temporal desynchronisation, circadian cognitive load, conversation velocity, and causal reachability — dimensions that LLMs do not reliably surface from inside the conversation.

Horizon ships two measurement planes. The conversation plane (above, always present) measures the health of a dialogue turn by turn. The optional mission plane — *Memento Mori* — measures elapsed calendar time against goals: ages, deadlines, stalls, per-entity latency, and share of a finite horizon. It is inert until you configure a store. See Mission plane.

Horizon is not a manipulation, sycophancy, or human-influence detector — it measures conversation *dynamics*, not whether an agent is steering or flattering the user. See LEGAL.md §1.

Why an external monitor? LLMs have *limited and unreliable* self-knowledge: introspection research shows partial self-access that is brittle and degrades on complex or out-of-distribution tasks (Binder et al. 2024; arXiv:2512.12411). So rather than depend on a model reporting its own conversation dynamics, Horizon measures them externally with cheap, deterministic, always-on arithmetic over a small local embedding model, with no LLM calls.


Why this exists

Multi-turn AI agents lose accuracy. The ICLR 2026 oral paper "LLMs Get Lost In Multi-Turn Conversation" (Laban, Hayashi, Zhou & Neville) reports an average 39% performance drop across six generation tasks when instructions arrive over multiple turns — a structural property that standard observability tools (LangSmith, RAGAS, DeepEval) cannot see because they measure responses, not conversations.

Horizon was built to close that gap. It is observability first: it surfaces conversation dynamics that response-level tools miss, using cheap deterministic arithmetic and a small local embedding model, with no LLM calls. In four controlled A/B scenarios where Horizon events drove a re-grounding intervention we measured a +15.7% composite quality lift and 87% fewer hallucination events — but those are *synthetic, scripted scenarios with a hand-tuned controller*, not a production result. Treat them as promising in-house evidence, not a guaranteed outcome (see Validation and LEGAL.md §5). Every signal — information gain, divergence, estimated ontological gap width, causal reachability — is a standard information-theory or arithmetic measure computed on text embeddings and timestamps; see 4D Spacetime Signals for the full definitions.


Getting started

Three paths — pick the one that fits your workflow:

Path 1 — Hosted MCP (fastest, zero install)

The fastest way to add Horizon to any Cursor, VS Code, or Claude Desktop workspace. No Python required.

Request an alpha key → open a Discussion, then add the config for your client:

Cursor (~/.cursor/mcp.json):

{

"mcpServers": { "horizon": { "url": "https://horizon.leocelis.com/sse", "headers": { "Authorization": "Bearer YOUR_KEY_HERE" } } } }

VS Code / GitHub Copilot (.vscode/mcp.json in your workspace):

{

"servers": { "horizon": { "type": "http", "url": "https://horizon.leocelis.com/sse", "headers": { "Authorization": "Bearer YOUR_KEY_HERE" } } } }

VS Code note: Use "servers" (not "mcpServers") and "type": "http" — VS Code tries Streamable HTTP first and falls back to SSE automatically, so "type": "http" works with the /sse URL.

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{

"mcpServers": { "horizon": { "url": "https://horizon.leocelis.com/sse", "headers": { "Authorization": "Bearer YOUR_KEY_HERE" } } } }

That's it. Reload your MCP client and three tools appear: new_conversation, process_turn, configure_session. With a mission store configured, seven more appear: clock_register, clock_progress, clock_status, clock_propose, clock_ack, clock_close, associate_mission (see Mission plane).

Alpha access: Horizon's hosted endpoint is in private alpha. Keys are distributed to agent developers who want to monitor real projects. Open a Discussion to request one — describe your use case and we'll send a key.

Path 2 — pip install (library integration)

Python 3.10–3.14.

pip install horizon-monitor

Verify your install (exercises the full pipeline on 5 canonical scenarios, ~25s):

horizon-validate
Path 3 — MCP server from source
git clone https://github.com/leocelis/horizon && cd horizon

pip install -e '.[mcp]' horizon serve # stdio — for Cursor, Claude Desktop horizon serve --transport sse --port 3847 # SSE — for web/team deployments

Add to ~/.cursor/mcp.json:

{

"mcpServers": { "horizon": { "command": "horizon", "args": ["serve"] } } }

Full Cursor and Claude Desktop setup guides: docs/integrations/


What it monitors

Standard observability tools evaluate individual response quality. Horizon evaluates conversation quality — a structurally different problem:

ToolWhat it seesWhat it misses
LangSmith, BraintrustLatency, cost, per-response qualityDeterministic, every-turn structural signals
RAGAS, DeepEvalFaithfulness, relevance per turn (DeepEval also has sampled multi-turn LLM-judge metrics)Zero-LLM-call, real-time scoring on every turn
Langfuse, Arize PhoenixSession-level LLM-judge evaluationDeterministic, always-on scoring at sub-50ms
Human ratersSubjective qualitySystematic structural decay
HorizonConversation dynamicsIntentionally nothing

Horizon does not replace per-response or LLM-judge quality tools. The differentiator is *how* it measures: deterministic, zero-LLM-call arithmetic on every single turn — effectively free and always-on — versus the alternative of sampled LLM-judge evaluations, which cost per sample and typically run offline or async rather than in real time.


Quickstart

from horizon_monitor import FidelityMonitor

from datetime import datetime, timezone

monitor = FidelityMonitor() session_id = monitor.new_conversation(metadata={"domain": "technical"})

result = monitor.process_turn( session_id, human_message="How does Python handle memory management?", agent_response="Python uses reference counting and a cyclic garbage collector...", timestamp=datetime.now(timezone.utc).isoformat(), )

print(f"Fidelity: {result.fidelity_score:.2f}") print(f"Health: {result.health_status}") print(f"Circadian factor: {result.circadian_factor:.2f}") print(f"Causal horizon: {result.reachable_turns} reachable turns") for event in result.events: print(f" Event: {event.type} (confidence={event.confidence:.2f})")


Framework integrations

OpenAI SDK
from openai import OpenAI

from horizon_monitor import FidelityMonitor

monitor = FidelityMonitor() session_id = monitor.new_conversation() client = monitor.wrap(OpenAI(), session_id)

response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Tell me about quantum computing."}] )

traj = monitor.get_trajectory(session_id) print(f"Fidelity: {traj.current_fidelity:.2f} T*: {traj.estimated_t_star}")

monitor.wrap() accepts custom timestamp and context providers for testing and replay.

Anthropic SDK
from anthropic import Anthropic

from horizon_monitor import FidelityMonitor

monitor = FidelityMonitor() session_id = monitor.new_conversation() client = monitor.wrap(Anthropic(), session_id)

response = client.messages.create( model="claude-3-5-sonnet-20241022", max_tokens=1024, messages=[{"role": "user", "content": "Explain RLHF."}] )

LangChain
from langchain_openai import ChatOpenAI

from horizon_monitor import FidelityMonitor from horizon_monitor.integrations.langchain import HorizonCallback

monitor = FidelityMonitor() session_id = monitor.new_conversation() callback = HorizonCallback(monitor, session_id)

llm = ChatOpenAI(callbacks=[callback]) llm.invoke("Explain the CAP theorem.") print(f"Fidelity: {callback.last_result.fidelity_score:.2f}")

OpenAI Agents SDK
from agents import Agent, Runner

from horizon_monitor import FidelityMonitor

monitor = FidelityMonitor() session_id = monitor.new_conversation() agent = Agent(name="assistant", model="gpt-4o-mini", instructions="You are helpful.")

for user_message in conversation: result = Runner.run_sync(agent, user_message) monitor.process_turn(session_id, human_message=user_message, agent_response=result.final_output, timestamp=datetime.now(timezone.utc).isoformat())


4D Spacetime Signals

"Spacetime" here is a metaphor, not physics. The relativity vocabulary (Minkowski interval,

light cone, proper time) is *design inspiration* — it shaped which quantities we compute. Every

signal below reduces to a standard information-theory or arithmetic measure on text embeddings and

timestamps, listed in the Plain definition column. Nothing in Horizon's behavior or validation

depends on the analogy being literally true, and the Lorentzian interval_class is emitted as

descriptive metadata only — no event or score depends on it.

Every process_turn() returns a TurnResult with 33 fields across six signal families:

Core (always present)
SignalDescription
fidelity_scoreComposite conversation health [0, 1]
igt_valueInformation Gain per Turn — semantic novelty
divergence_scoreJensen-Shannon proxy for intent/response gap
twr_valueToken Waste Ratio — semantic redundancy
consistency_scoreBipredictability — structural coherence
epsilon_tEstimated ontological gap width [0, 1]
health_statushealthy / degrading / critical / converged
conversation_modeexecute / explore / refine / learn (auto-detected)
Temporal (requires timestamp)
SignalDescription
gap_secondsWall-clock gap since last turn
estimated_retentionHuman memory retention (Ebbinghaus half-life model)

| circadian_factor | Human cogn

Only the beginning is shown; read the rest in the repo