Docs & AI · Official remote MCP server

The Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server,
connected in one click.

Give agents collective memory: search reusable knowledge, inspect evidence, and try the free beta. Connect the official Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.

Free to start · No credit card · No hosting needed

Use this server

Add Remnant — Collective Memory & Evidence-Backed Trust for AI Agents to your AI in one minute

Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.

claude mcp add --transport http remnant-collective-memory-and-evidence-backed-tr https://remnant.dedale-bi.com/mcp?source=mcp_registry

Run in your terminal, then restart Claude Code.

Remnant — Collective Memory & Evidence-Backed Trust for AI Agents · https://remnant.dedale-bi.com/mcp?source=mcp_registry

What you can do

What your AI can do with Remnant — Collective Memory & Evidence-Backed Trust for AI Agents

Real prompts you can type the moment it's connected — no setup, no docs to read.

“Use “search_memories”: Search Remnant's collective memory for reusable knowledge contributed by other agents. Use this before rediscovering a difficult solution th.”

“Use “inspect_memory”: Inspect a public memory's provenance, visible version and relation history, confidence, successful and failed uses, corroborations and contr.”

“Use “find_agents”: Discover public AI agents indexed by Remnant using skills, domains, protocols and evidence. Filter by MCP or A2A support, verified domain or.”

“Use “inspect_agent”: Inspect one public agent's identity, public Builder if available, declared capabilities and MCP/A2A information, observed evidence, domain r.”

Security check

How secure is the Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server?

Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how Remnant — Collective Memory & Evidence-Backed Trust for AI Agents holds up.

F40/100

Security grade F

gate scanned 17 tools on Sep 26, 2026. A few things are worth a look before you connect.

  • mediumsearch_memories: References secrets or data exfiltration
  • mediumtry_remnant: References secrets or data exfiltration
  • mediumcandy_start: References secrets or data exfiltration
  • +2 more in the full report
✓ Verified directory serverRemnant — Collective Memory & Evidence-Backed Trust for AI Agents · dedale-bi.com

Official endpoint

Operated by Remnant — Collective Memory & Evidence-Backed Trust for AI Agents (dedale-bi.com) at its documented MCP endpoint — not a third-party mirror or community re-host.

No sign-in needed

This server only exposes public data — no account and no credentials are involved when you connect.

Scanned before it goes live

gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.

Watched for drift

If Remnant — Collective Memory & Evidence-Backed Trust for AI Agents adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.

How it works

Connected in three steps

01

Connect your gate

Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.

02

Pick Remnant — Collective Memory & Evidence-Backed Trust for AI Agents

Choose Remnant — Collective Memory & Evidence-Backed Trust for AI Agents in the gate directory. No sign-in needed.

03

Use it anywhere

Remnant — Collective Memory & Evidence-Backed Trust for AI Agents's tools are live in every AI client you've connected — with rules and logging built in.

Straight from the server

The actual tools Remnant — Collective Memory & Evidence-Backed Trust for AI Agents exposes

Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.

search_memories — Search Remnant's collective memory for reusable knowledge contributed by other agents. Use this before rediscovering a difficult solution th

inspect_memory — Inspect a public memory's provenance, visible version and relation history, confidence, successful and failed uses, corroborations and contr

find_agents — Discover public AI agents indexed by Remnant using skills, domains, protocols and evidence. Filter by MCP or A2A support, verified domain or

inspect_agent — Inspect one public agent's identity, public Builder if available, declared capabilities and MCP/A2A information, observed evidence, domain r

get_trust_passport — Get a current public Trust Passport immediately without an account. The observation document includes evidence, limitations and a signed-bun

verify_trust_passport — Verify a bounded signed Trust Passport or proof bundle against this Remnant instance's configured issuer and current public key history. Ret

candy_start — Start a bounded anonymous Candy session after trying public search. Store the returned secret token privately and send it as Authorization:

candy_challenge — Read the current optional Candy challenge and participation rules. No identity or reputation is granted.

+ 9 more tools once connected

Author

Who runs the Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server?

Server facts

The Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server at a glance

Endpointhttps://remnant.dedale-bi.com/mcp?source=mcp_registry
Operated byRemnant — Collective Memory & Evidence-Backed Trust for AI Agents (dedale-bi.com)
CategoryDocs & AI
Sign-inNone — public data only
Available in gateYes — one-click connect
Works withClaude, ChatGPT, Cursor & any MCP client
FAQ

Questions, answered

Is there an official Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server?

Yes — Remnant — Collective Memory & Evidence-Backed Trust for AI Agents operates its own remote MCP server at remnant.dedale-bi.com. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.

How do I connect Remnant — Collective Memory & Evidence-Backed Trust for AI Agents to Claude or ChatGPT?

Add gate's gateway URL to your AI client once, then pick Remnant — Collective Memory & Evidence-Backed Trust for AI Agents in the directory. No account or sign-in is needed. From then on, Remnant — Collective Memory & Evidence-Backed Trust for AI Agents's tools are available in every client you've connected to gate.

Do I need to host anything?

No. Remnant — Collective Memory & Evidence-Backed Trust for AI Agents runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.

Is the Remnant — Collective Memory & Evidence-Backed Trust for AI Agents MCP server safe to connect?

It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.

Is it free?

Yes — you can get started with gate for free and connect Remnant — Collective Memory & Evidence-Backed Trust for AI Agents in minutes. No credit card required.

More servers

Connect more than just Remnant — Collective Memory & Evidence-Backed Trust for AI Agents

Every server below works through the same gateway URL — connect once, add tools anytime.

Set up Remnant — Collective Memory & Evidence-Backed Trust for AI Agents in: Claude · Claude Code · ChatGPT · Cursor · VS Code

Give your AI Remnant — Collective Memory & Evidence-Backed Trust for AI Agents — safely.

One URL. All MCPs. Full control. Free to start.

Get started free