# Slid Phi Labs (remote · www.slidphilabs.com)

CuNi exactness, Chamber two-key JSON, Agent-Rider. Lab signup, agent keys, x402 catalog.

- Trust score: 69/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `www.slidphilabs.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www.md), [page](https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www)

## Channel facts

- Endpoint: `https://www.slidphilabs.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.20.2`

## 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 2026-09-21.

- **Endpoint Security**: 57/100
  - 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 42 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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 (fair).
  - Tool/resource definitions use about 1614 tokens (~38/item across 42 items; 42 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 13% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 42 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 42 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 Slid Phi Labs MCP server?

Slid Phi Labs is a hosted endpoint at https://www.slidphilabs.com/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 ceedot-rock-slid-phi-labs 'https://www.slidphilabs.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ceedot-rock-slid-phi-labs": {
      "url": "https://www.slidphilabs.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ceedot-rock-slid-phi-labs": {
      "type": "http",
      "url": "https://www.slidphilabs.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ceedot-rock-slid-phi-labs]
url = "https://www.slidphilabs.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ceedot-rock-slid-phi-labs": {
      "type": "remote",
      "url": "https://www.slidphilabs.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ceedot-rock-slid-phi-labs --url 'https://www.slidphilabs.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ceedot-rock-slid-phi-labs:
    url: "https://www.slidphilabs.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ceedot-rock-slid-phi-labs": {
      "Transport": "http",
      "Url": "https://www.slidphilabs.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ceedot-rock-slid-phi-labs -t streamable-http -u 'https://www.slidphilabs.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ceedot-rock-slid-phi-labs": {
      "type": "http",
      "url": "https://www.slidphilabs.com/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.

### 2026-09-21 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 67, +4)

- [functional improvement] MCP protocol: fail → pass
- [functional] MCP protocol version: 2024-11-05 → 2025-11-25

### 2026-09-15 (score 63, +1)

- [security] Tool “aware_get” rewrote its description, which is the text the model reads
- [security] Tool “aware_search” rewrote its description, which is the text the model reads
- [security] Tool “pcc_get” rewrote its description, which is the text the model reads
- [security] Tool “pcc_search” rewrote its description, which is the text the model reads
- [cosmetic] “spl_quote” reworded the description of “bytes”

### 2026-09-14 (score 62, 0)

- [functional regression] Schema quality: 1402 → 1589
- [functional improvement] Tool coverage: 8% → 13%
- [functional] Server version: 1.20.1 → 1.20.2
- [functional] New tool “cuni_bank”
- [functional] New tool “pcc_get”
- [functional] New tool “pcc_search”

### 2026-09-13 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 61, 0)

- [security] Tool “aware_get” rewrote its description, which is the text the model reads
- [security] Tool “aware_search” rewrote its description, which is the text the model reads

### 2026-09-11 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (42)

### `cuni_bank` (~114 tokens)

CuNi Bank: paste N, get X. Ingest → emit → prove, or refuse. v1 from Python. Args: source, from (py|cuni), to (catalog id, e.g. js). POSTs to cuni-studio /api/bank.

Input parameters:

- `from` (string): py | cuni
- `source` (string, required): Source program (Python v1 subset or .cuni)
- `to` (string, required): catalog id: py, go, js, ts, …

### `spl_discover` (~22 tokens)

Lead product, cash product, auth, MCP, x402.

### `spl_lab_auth` (~20 tokens)

How to mint a lab account or agent API key.

### `spl_signup` (~18 tokens)

Create a human lab account (email + password).

### `spl_agent_key` (~18 tokens)

Mint an agent API key (no password).

### `spl_catalog` (~18 tokens)

Standing SKUs agents can buy via x402.

### `spl_compress` (~38 tokens)

Hosted lossless compression. Every dual-licensed pathway on this machine. Args: data_b64.

Input parameters:

- `data_b64` (string, required)

### `spl_decompress` (~32 tokens)

Restore bytes packed by spl_compress. Args: packed_b64.

Input parameters:

- `packed_b64` (string, required)

### `spl_zip` (~44 tokens)

Pack files into a .pcc archive (our zip). Args: files: [{path, data_b64}]. Returns packed_b64.

Input parameters:

- `files` (array, required)

### `spl_unzip` (~44 tokens)

Restore files from a .pcc archive. Args: packed_b64. Returns files: [{path, data_b64}].

Input parameters:

- `packed_b64` (string, required)

### `spl_quote` (~100 tokens)

Suite quote. First 2 GB/month free, then 8¢/GB, $1 card minimum. Args: bytes, product, op.

Input parameters:

- `bytes` (number): Payload bytes. first 2 GB/month free.
- `dataClass` (string)
- `op` (string): compress | decompress | roundtrip
- `product` (string): auto | zrw | blackjack | shard-zip | shard-tsdb | slid-phi

### `spl_warrant_issue` (~103 tokens)

Issue a Warrant (mandate) for a Rider identity. Pass rider JWT, or demo:true for a 10-minute shape check. Complements Agent-Rider.

Input parameters:

- `actions` (array)
- `allow_hosts` (array)
- `demo` (boolean)
- `max_calls` (number)
- `max_usd` (number)
- `rider` (string): X-Agent-Rider JWT
- `ttl_seconds` (number)

### `spl_warrant_verify` (~42 tokens)

Verify a Warrant token. Optional host and action.

Input parameters:

- `action` (string)
- `host` (string)
- `warrant` (string)

### `spl_warrant_receipt` (~75 tokens)

File a receipt against a Warrant after an action.

Input parameters:

- `action` (string)
- `host` (string)
- `note` (string)
- `request_sha256` (string)
- `result_sha256` (string)
- `usd` (number)
- `warrant` (string)

### `sku_search` (~34 tokens)

Prices — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `sku_get` (~27 tokens)

Prices — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `license_search` (~34 tokens)

License — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `license_get` (~27 tokens)

License — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `surface_search` (~37 tokens)

Where to use them — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `surface_get` (~30 tokens)

Where to use them — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `cuni_search` (~36 tokens)

CuNi — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `cuni_get` (~29 tokens)

CuNi — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `chamber_search` (~34 tokens)

Chamber — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `chamber_get` (~27 tokens)

Chamber — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `rider_search` (~36 tokens)

Agent-Rider — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `rider_get` (~29 tokens)

Agent-Rider — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `aware_search` (~42 tokens)

PCC (AWARE is a retired alias) — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `aware_get` (~35 tokens)

PCC (AWARE is a retired alias) — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `pulsar_search` (~36 tokens)

pulsar — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `pulsar_get` (~29 tokens)

pulsar — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `measure_search` (~37 tokens)

How pulsar compares — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `measure_get` (~30 tokens)

How pulsar compares — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `rail_search` (~36 tokens)

How to pay — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `rail_get` (~29 tokens)

How to pay — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `box_search` (~34 tokens)

Try — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `box_get` (~27 tokens)

Try — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `npm_search` (~37 tokens)

npm / public packages — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `npm_get` (~30 tokens)

npm / public packages — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `docs_search` (~34 tokens)

Docs — what it is, what you get, what you pay. Free text or code.

Input parameters:

- `q` (string)

### `docs_get` (~27 tokens)

Docs — one entry with notes, price, and links.

Input parameters:

- `id` (string, required)

### `pcc_search` (~45 tokens)

PCC — what it is, what you get, what you pay. Free text or code. Prefer this. aware_search is a retired alias.

Input parameters:

- `q` (string)

### `pcc_get` (~38 tokens)

PCC — one entry with notes, price, and links. Prefer this. aware_get is a retired alias.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www#diagnostics

## Score history

- 2026-09-21: 69
- 2026-09-20: 68
- 2026-09-19: 68
- 2026-09-18: 67
- 2026-09-17: 67
- 2026-09-16: 63
- 2026-09-15: 63
- 2026-09-14: 62
- 2026-09-13: 62
- 2026-09-12: 61
- 2026-09-11: 61
- 2026-09-10: 60
- 2026-09-09: 60
- 2026-09-08: 59
- 2026-09-07: 58
- 2026-09-06: 58
- 2026-09-05: 57
- 2026-09-04: 57
- 2026-09-03: 57
- 2026-09-02: 61
- 2026-09-01: 60
- 2026-08-31: 60
- 2026-08-30: 59

## Common questions

### What is the Slid Phi Labs MCP server?

Slid Phi Labs is an MCP server listed in the public MCP registry as io.github.ceedot-rock/slid-phi-labs. CuNi exactness, Chamber two-key JSON, Agent-Rider. Lab signup, agent keys, x402 catalog. This page covers its hosted endpoint (https://www.slidphilabs.com/mcp).

### Is the Slid Phi Labs MCP server safe to use?

Slid Phi Labs scores 69 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 Slid Phi Labs MCP server expose?

Slid Phi Labs exposes 42 tools: cuni_bank, spl_discover, spl_lab_auth, spl_signup, spl_agent_key, and 37 more. Their descriptions and schemas cost roughly 1,614 tokens of context every time the server is loaded.

### Does the Slid Phi Labs MCP server require authentication?

No. We connected to Slid Phi Labs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Slid Phi Labs MCP server still maintained?

Slid Phi Labs is still listed as active in the MCP registry. We last reached this channel on 21 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://www.slidphilabs.com/mcp
- Website: https://www.slidphilabs.com/
- Changelog RSS feed: https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www.json
- HTML version of this page: https://verifymcp.io/servers/ceedot-rock-slid-phi-labs/www