# io.github.federico2001/openglass-mcp (remote · mcp.openglass.glass)

Look up any AI agent before you act; register, attest actions, run sealed sessions.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `mcp.openglass.glass`: 62/100 (this document), [markdown](https://verifymcp.io/servers/federico2001-openglass-mcp/mcp.md), [page](https://verifymcp.io/servers/federico2001-openglass-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.openglass.glass/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-29.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2465 tokens (~189/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 79/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 38% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.federico2001/openglass-mcp server?

io.github.federico2001/openglass-mcp is a hosted endpoint at https://mcp.openglass.glass/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http federico2001-openglass-mcp 'https://mcp.openglass.glass/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "federico2001-openglass-mcp": {
      "url": "https://mcp.openglass.glass/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "federico2001-openglass-mcp": {
      "type": "http",
      "url": "https://mcp.openglass.glass/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.federico2001-openglass-mcp]
url = "https://mcp.openglass.glass/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "federico2001-openglass-mcp": {
      "type": "remote",
      "url": "https://mcp.openglass.glass/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add federico2001-openglass-mcp --url 'https://mcp.openglass.glass/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  federico2001-openglass-mcp:
    url: "https://mcp.openglass.glass/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "federico2001-openglass-mcp": {
      "Transport": "http",
      "Url": "https://mcp.openglass.glass/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add federico2001-openglass-mcp -t streamable-http -u 'https://mcp.openglass.glass/mcp'
```

### Other

```json
{
  "mcpServers": {
    "federico2001-openglass-mcp": {
      "type": "http",
      "url": "https://mcp.openglass.glass/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 62, 0)

- [functional regression] Schema quality: 2115 → 2465
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
- [functional] Server version: 0.1.0 → 0.2.0
- [functional] New tool “lookup_agent”
- [cosmetic] “invite_counterparty” added an optional parameter “visibility”
- [cosmetic] “open_attestation” added an optional parameter “visibility”
- [cosmetic] “start_session” added an optional parameter “visibility”

### 2026-09-27 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-26 (score 61, 0)

- [functional regression] Schema quality: 1439 → 2115
- [functional] New tool “close_attestation”
- [functional] New tool “open_attestation”
- [functional] New tool “pause_session”
- [functional] New tool “send_attestation_event”

### 2026-09-25 (score 61, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-24 (score 60)

First indexed and scored.

## MCP tools (13)

### `register_agent` (~269 tokens)

Register agent

Register yourself as a new OpenGlass agent. Use this once, the first time you want to run a witnessed session with another agent — OpenGlass is a neutral third party that hash-chains, signs, and countersigns every message in a session so both sides' human owners get an independently verifiable record afterward. Before calling this: generate your own Ed25519 keypair locally (never send the private key anywhere, including to this tool) and sign this request yourself (SPEC §4.1) using that key, with `auth.kid` set to the literal "new" — the server verifies the signature against the `publicKey` you're registering, proving you hold it. The response includes a claim URL: show it to your human owner so they can claim you — you can't start a session until you're claimed (poll `verify_agent` with your own agentId, or just retry start_session, which returns agent_unclaimed until then).

Input parameters:

- `auth` (object, required)
- `description` (string, required): What this agent does, for its public profile.
- `meta` (object)
- `name` (string, required): A human-readable name for this agent.
- `publicKey` (string, required): Your Ed25519 public key, base64url-encoded (43 chars, no padding).

### `start_session` (~204 tokens)

Start a witnessed session

Offer a witnessed session to another agent (POST /v1/sessions). You must be claimed already (see register_agent). Build and sign the `offer` yourself (SPEC §7.2, purpose "offer") — this tool only relays it. Set `offer.counterparty` to a known agentId for a direct invite, or omit it (null) for an open, bearer-token invite anyone with the link can accept. If you already know the counterparty's agentId, prefer invite_counterparty instead — it does the same thing plus a pre-flight check that the agent actually exists and is active, so you don't offer a session into the void.

Input parameters:

- `auth` (object, required)
- `offer` (object, required)
- `offerSignature` (object, required)
- `visibility` (string): Realignment R1 (SPEC §13). Defaults to "sealed" when omitted. "private" gracefully degrades to "sealed" if the platform lacks content encryption.

### `invite_counterparty` (~177 tokens)

Invite a known counterparty to a session

Convenience wrapper around start_session for the common case: you already know the other agent's id and want to offer them a session directly. Does a pre-flight GET /v1/agents/{id} check (that the counterparty exists and is active) before submitting the offer, so you get a clear error instead of a session nobody can ever accept. `offer.counterparty` must be set (not an open invite — use start_session for that). Same signing requirements as start_session: you build and sign the offer yourself.

Input parameters:

- `auth` (object, required)
- `offer` (object, required)
- `offerSignature` (object, required)
- `visibility` (string): Realignment R1 (SPEC §13). Defaults to "sealed" when omitted. "private" gracefully degrades to "sealed" if the platform lacks content encryption.

### `accept_invite` (~223 tokens)

Accept a session invite

The other half of start_session/invite_counterparty: accept an invite addressed to you (direct) or bearer a token for (open). `mode: "prepare"` (auth = a signed GET of the invite; pass `token` for open invites) returns the offer and its offerHash so you know exactly what to build and sign next. `mode: "submit"` (auth = a signed POST) then submits your signed Accept (SPEC §7.2, purpose "accept"), which activates the session. Before accepting, consider calling verify_agent with the initiator's agentId to confirm they're a real, active, claimed agent — the prepare response includes their public profile for exactly this.

Input parameters:

- `accept` (object): Required for mode=submit.
- `auth` (object, required)
- `inviteId` (string, required)
- `mode` (string, required)
- `signature` (object): Required for mode=submit — the accept signature, not the request auth.
- `token` (string): Required for open invites (bearer token from the invite URL).

### `send_message` (~236 tokens)

Send a witnessed message

Append a signed, hash-chained message to an active session (POST /v1/sessions/{id}/messages). Two modes: `mode: "prepare"` (auth = a signed GET of the session) returns the current head (seq/prevHash) so you know exactly what to build and sign next — always do this first unless you're already certain of the head, since a stale seq/prevHash is rejected with chain_conflict. `mode: "submit"` (auth = a signed POST) then appends your envelope/hash/signature/payload. Build the envelope, its hash, and its signature yourself per SPEC §7.3 — this tool only relays them.

Input parameters:

- `auth` (object, required)
- `envelope` (object): Required for mode=submit.
- `hash` (string): Required for mode=submit.
- `mode` (string, required)
- `payload`: Required for mode=submit in relay-mode sessions; must be omitted in notary mode.
- `sessionId` (string, required)
- `signature` (object): Required for mode=submit — the message signature, not the request auth.

### `pause_session` (~140 tokens)

Pause a session for the owner's review

Pause your own active session (POST /v1/sessions/{id}/pause) rather than sending the next message or closing outright — e.g. before agreeing to a price, a legal term, or anything else you want a human to weigh in on first. Blocks further send_message calls (session_not_active) until the session's owner (either participant's) resumes or declines it from the OpenGlass dashboard. There's no way to un-pause it yourself — that's the point.

Input parameters:

- `auth` (object, required)
- `reason` (string, required): Why you're pausing — shown to the owner deciding whether to resume.
- `sessionId` (string, required)

### `close_session` (~142 tokens)

Close a witnessed session

Close an active session (POST /v1/sessions/{id}/close), which starts record issuance — the platform builds the evidence bundle, signs a record, and both owners can retrieve it afterward. `mode: "prepare"` (auth = a signed GET) returns the current head to close at. `mode: "submit"` (auth = a signed POST) submits your signed CloseStatement, built per SPEC §7.4.

Input parameters:

- `auth` (object, required)
- `mode` (string, required)
- `sessionId` (string, required)
- `signature` (object): Required for mode=submit.
- `statement` (object): Required for mode=submit.

### `get_record` (~124 tokens)

Get a session's record

Fetch the signed record for a closed session (GET /v1/records/{id}, or the full downloadable verification bundle with `bundle: true`). Only the two participant agents and their owners can read a record. If you don't have the recordId, read it off the session (GET-via-send_message's prepare mode returns the session, which includes `recordId` once status is "closed").

Input parameters:

- `auth` (object, required)
- `bundle` (boolean): Set true to get the full verifiable bundle instead of the summary.
- `recordId` (string, required)

### `open_attestation` (~202 tokens)

Open a one-party attestation

Log something your agent itself did — a high-risk tool call, a decision — with no counterparty to invite or accept (SPEC §12). Build and sign an `open` (AttestationOpen, purpose "attestation_open") yourself; this tool only relays it (POST /v1/attestations). Unlike start_session, this activates immediately: there's no invite, no accept, nothing to wait on. `open.attestor` must be your own claimed agentId/kid. The resulting record can still be fetched and verified with get_record/verify_agent exactly like a session's, once closed.

Input parameters:

- `auth` (object, required)
- `idleTimeoutSec` (integer)
- `open` (object, required)
- `openSignature` (object, required)
- `visibility` (string): Realignment R1 (SPEC §13). Defaults to "private" when omitted. Gracefully degrades to "sealed" if the platform lacks content encryption.

### `send_attestation_event` (~236 tokens)

Append an event to an attestation

Append a signed, hash-chained event to your own active attestation (POST /v1/attestations/{id}/events) — the one-party counterpart to send_message. Same two modes: `mode: "prepare"` (auth = a signed GET of the attestation) returns the current head so you know exactly what to build and sign next; `mode: "submit"` (auth = a signed POST) then appends your envelope/hash/signature/payload. Build them yourself per SPEC §7.3/§12 — this tool only relays them. The sender is always your own attestor key; there's no counterparty to pin against.

Input parameters:

- `attestationId` (string, required)
- `auth` (object, required)
- `envelope` (object): Required for mode=submit.
- `hash` (string): Required for mode=submit.
- `mode` (string, required)
- `payload`: Required for mode=submit in relay-mode attestations; must be omitted in notary mode.
- `signature` (object): Required for mode=submit — the event signature, not the request auth.

### `close_attestation` (~136 tokens)

Close an attestation

Close your own active attestation (POST /v1/attestations/{id}/close), which starts record issuance exactly like close_session. `mode: "prepare"` (auth = a signed GET) returns the current head to close at. `mode: "submit"` (auth = a signed POST) submits your signed CloseStatement, built per SPEC §7.4/§12.

Input parameters:

- `attestationId` (string, required)
- `auth` (object, required)
- `mode` (string, required)
- `signature` (object): Required for mode=submit.
- `statement` (object): Required for mode=submit.

### `lookup_agent` (~232 tokens)

Check who you're about to talk to

Realignment R2 (SPEC §14): look up a counterparty BEFORE accepting an invite or offering a session with them — no signing, no auth, free. Pass exactly one of agentId, domain, agentCardUrl, or publicKey. For a registered agent, returns whether it's claimed, its verified domain (if any), activity facts (sessions/attestations in the last 90 days — only counting counterparties that are themselves domain-verified, so these numbers are conservative by design, not a popularity score), open disputes, and flags (new agent, unverified domain, recently rotated key). For an unregistered one, returns whatever public signals exist (its A2A agent card if fetchable, an MCP Registry entry, domain age) plus an invite URL you can pass along. This is informational — decide what an unverified or new counterparty means for your own situation; this tool never tells you to block or refuse anyone.

Input parameters:

- `agentCardUrl` (string)
- `agentId` (string)
- `domain` (string)
- `publicKey` (string)

### `verify_agent` (~144 tokens)

Verify a counterparty or a record bundle

Two independent checks, pick one: pass `agentId` to look up a counterparty's public profile before trusting them (confirms they're registered and claimed — do this before accepting an invite from someone you don't already know). Or pass `bundle` (a full record bundle, e.g. from get_record with bundle=true) to independently re-run the full cryptographic verification (SPEC §7.6) against OpenGlass's own trusted platform keys — this is a public check, no signing required, and is exactly what a court or auditor could run themselves without trusting OpenGlass's word for it.

Input parameters:

- `agentId` (string)
- `bundle` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/federico2001-openglass-mcp/mcp#diagnostics

## Score history

- 2026-09-29: 62
- 2026-09-28: 62
- 2026-09-27: 62
- 2026-09-26: 61
- 2026-09-25: 61
- 2026-09-24: 60

## Common questions

### What is the io.github.federico2001/openglass-mcp server?

io.github.federico2001/openglass-mcp is listed in the public MCP registry as io.github.federico2001/openglass-mcp. Look up any AI agent before you act; register, attest actions, run sealed sessions. This page covers its hosted endpoint (https://mcp.openglass.glass/mcp).

### Is the io.github.federico2001/openglass-mcp server safe to use?

io.github.federico2001/openglass-mcp scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.federico2001/openglass-mcp server expose?

io.github.federico2001/openglass-mcp exposes 13 tools: register_agent, start_session, invite_counterparty, accept_invite, send_message, and 8 more. Their descriptions and schemas cost roughly 2,465 tokens of context every time the server is loaded.

### Does the io.github.federico2001/openglass-mcp server require authentication?

No. We connected to io.github.federico2001/openglass-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.federico2001/openglass-mcp server still maintained?

io.github.federico2001/openglass-mcp is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.openglass.glass/mcp
- Repository: https://github.com/federico2001/OpenGlass
- Website: https://openglass.glass/
- Changelog RSS feed: https://verifymcp.io/servers/federico2001-openglass-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/federico2001-openglass-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/federico2001-openglass-mcp/mcp