rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Skill · How-to guide
AgentProof
What it does
Free hosted notary: make any AI agent's actions provable in one call. Verify signed agent logs.
- Connects Runs in the cloud
- Account or key No key needed
- Category Developer tools
Use together with
Skills that teach the AI this kind of work; they work alongside this one
archify
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
Skill · How-to guide
Why it ranks here
This one is in the “Apps that connect to AI” tab, which is ordered without stars, in this order
| 1. In Claude’s connector directory | No | |
|---|---|---|
| 2. Tried by our team | No | |
| 3. Works for Thai users | No | |
| 4. Usage without stars | 20/100 | Popularity 0 · Freshness 12 · Still answering 8 |
| 5. Listed on | 2026-11-15 |
Quality: Passed 4/5 basic checks (shown, not used for ordering)
Install
Pick the AI app you use, then copy the settings.
Passed 4/5 checks · What you ask goes through the maker’s server (agentproofchain.com) · ✓ Commands checked Nov 14, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · 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
Open Claude’s Connectors page
CustomizeConnectors
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 · NameAgentProofRemote MCP server URL · Addresshttps://agentproofchain.com/mcpClick 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
Turn it on in a chat
+ConnectorsAgentProof
Try it
Use AgentProof and tell me what you can do for me, then show me one thing✓ If Claude says it is using AgentProof or shows a AgentProof 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 ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Open ChatGPT’s add-MCP page on the web
Plugins+Add custom MCP server
Fill in the name and address
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
Name · NameAgentProofConnection · Addresshttps://agentproofchain.com/mcpPick AgentProof in a chat
Start a new chat and pick AgentProof from your plugins before typing
Try it
Use AgentProof and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using AgentProof or shows a AgentProof tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --transport http --scope user agentproof https://agentproofchain.com/mcpType /mcp in Claude Code
You should see AgentProof listed as connected
Try it
Use AgentProof and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using AgentProof or shows a AgentProof 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 2 min
No key, nothing to install
Open the AI chat in Cursor in Agent mode
Try it
Use AgentProof and tell me what you can do for me, then show me one thing✓ If Cursor says it is using AgentProof or shows a AgentProof 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 2 min
No key, nothing to install
Open the AI chat in VS Code in Agent mode
Try it
Use AgentProof and tell me what you can do for me, then show me one thing✓ If VS Code says it is using AgentProof or shows a AgentProof 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.
Address for apps that connect over the web
Address
https://agentproofchain.com/mcpJSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Over the web
Claude Code
claude mcp add --transport http --scope user agentproof https://agentproofchain.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"agentproof": {
"url": "https://agentproofchain.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"agentproof": {
"type": "http",
"url": "https://agentproofchain.com/mcp"
}
}
}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
- Verified domain
- ✓ agentproofchain.com
- Connection
- Runs in the cloud
- Transport
- streamable-http
- Latest versioni
- 0.3.0
- Categoryi
- Developer tools
- Published to registryi
- Nov 15, 2026
- Code last changedi
- Aug 18, 2026
- Maker
- cipherxsniper
- Website
- agentproofchain.com
- 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
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
Related guides
What it can do
Tool names and descriptions exactly as the server reported them on Nov 14, 2026. The maker wrote them, not us; we show them as plain text.
verify_logVerify an AgentProof log (JSONL, one signed entry per line) against the signer's base64 Ed25519 public key. Checks every signature and every hash link; reports VALID or the first entry that was edited, removed, inserted or forged. The log is checked in memory and not stored.
lanturn_liveLive proof: Lanturn is a town of ~45 AI agents whose every action is signed by AgentProof within a minute. Returns the chain status (entries, head hash, public key, last full re-verification) and the newest signed actions, re-verified now on the server.
get_startedHow to add AgentProof to an agent: Claude Code plugin, any MCP client, Python, LangChain, or verifying a log with zero installs.
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 16, 2026
- ! Caution
Maker matches the repo
The publisher (agentproofchain.com) is not the repo owner (cipherxsniper); someone else may have listed it
- ✓ Pass
Still maintained
Code last changed 3 months ago
- ✓ Pass
Has a licence
Uses MIT
- ✓ Pass
- – Not applicable
Sign-in with OAuth
No sign-in needed
- ✓ Pass
No hidden instructions in tool descriptions
Read 3 tool descriptions and found no hidden instructions to the AI
Makers: ask for a re-check or report wrong info
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.
User reviews
No reviews yet
Compared with others in Developer toolsi
- More stars than 0% of the other 5938 servers in this category
- Published to the registry more recently than 98% of the other 5938 servers in this category
- Basic checks equal to or better than 50% of the other 5938 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 AgentProof safe?
It passed 4 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?
The registry does not list a required key, though some servers ask you to sign in on first use.
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 months ago, and the latest version (0.3.0) reached the registry yesterday.
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: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
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
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Runs in the cloud✓ service owner · gitdiagram.comTried by the PopNx team
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Runs in the cloud✓ service owner · appllama.io
Cloudflare MCP
Cloudflare MCP servers
Runs in the cloud✓ service owner · mcp.cloudflare.comTried by the PopNx team
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Runs in the cloud✓ service owner · omnara.com
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
Computer or cloud✓ service owner · repowise.dev
- GitDiagram — Runs in the cloud, nothing to install · No key needed
- Appllama — Runs in the cloud, nothing to install · No key needed
- Cloudflare MCP — Runs in the cloud, nothing to install · No key needed · In Claude’s directory
- Omnara — Runs in the cloud, nothing to install · No key needed
- Repowise — Cloud or install on your computer · No key needed
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.
agentproof
Cryptographically signed, tamper-evident audit logs for autonomous agents.
As more tools let AI agents run code, call APIs, and modify files autonomously, there's usually no way to verify — after the fact, or from outside the agent's own self-report — what it actually did. agentproof gives any agent a way to sign every action it takes into a hash-chained log, so the record can be independently verified by anyone, without trusting the agent's own summary of events.
Each log entry is signed with Ed25519 and references the SHA-256 hash of the entry before it. Editing, deleting, or inserting an entry breaks the chain in a way verify() will always catch.
Install
pip install agentproofQuick start
from agentproof import sign_event, verify_logsign_event( "agent.log", "tool_call", {"tool": "read_file", "args": {"path": "config.yaml"}}, )
ok, message = verify_log("agent.log") print(ok, message) # True, "1 entries verified, chain intact"
Or with the class wrapper, if you're signing many events against the same log and key:
from agentproof import ProofChainchain = ProofChain("agent.log", signing_key=my_key_bytes) chain.sign_event("tool_call", {"tool": "run_bash", "cmd": "pytest"}) chain.sign_event("model_decision", {"chose": "retry", "reason": "timeout"}) ok, msg = chain.verify()
Keys
Generate a key:
agentproof keygenAGENTPROOF_SIGNING_KEY=
agentproof resolves a signing key in this order:
signing_key=passed directly to a function call (raw bytes or base64 str)AGENTPROOF_SIGNING_KEYenvironment variable (base64) — works on platforms with no persistent filesystem (Render, Fly, Lambda, etc.)keyfile=passed directly (path to a JSON file:{"secret": [...]}or a raw JSON array of 32 ints)AGENTPROOF_KEYFILEenvironment variable (path to the same format)
No placeholder key is ever silently substituted — if none of the above resolve, you get a clear ProofChainError.
Verifying someone else's log
If you didn't sign the log yourself, verify it against the signer's published public key instead of your own private key:
from agentproof import verify_logimport base64
pubkey = base64.b64decode("their-published-public-key==") ok, msg = verify_log("their_agent.log", pubkey_bytes=pubkey)
Publish your own public key with:
agentproof pubkeyCLI
agentproof keygen # generate a new keyagentproof verify path/to/agent.log # verify using your own resolved key agentproof verify log.jsonl --pubkey B64 # verify against a specific public key agentproof pubkey # print your public key to share
What this doesn't do
agentproof proves that a specific key signed a specific sequence of events, and that the sequence hasn't been altered since. It does not verify that the *content* of an event is true — if an agent lies about what a tool call returned and then signs that lie, the signature is still valid. Signing happens at the point your code calls sign_event, so the honesty guarantee is only as strong as what you choose to log and when.
License
MIT