# ICONIC Intelligence Reserve — Free Agent Assessment (remote · patrick-beastmaster.tailf32530.ts.net)

Free agent assessment and a one-hour synthetic Reserve sandbox with outcome tracing.

- Trust score: 65/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

> **Recent critical change**: Authorization (2026-11-12). See the changelog below before you install this server.

## Components

- remote · `patrick-beastmaster.tailf32530.ts.net`: 65/100 (this document), [markdown](https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp.md), [page](https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp)

## Channel facts

- Endpoint: `https://patrick-beastmaster.tailf32530.ts.net/reserve/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 2026-11-21.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (reserve_sandbox_release).
  - 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**: 51/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1412 tokens (~52/item across 27 items; 27 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 27 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 28 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 ICONIC Intelligence Reserve — Free Agent Assessment MCP server?

ICONIC Intelligence Reserve — Free Agent Assessment is a hosted endpoint at https://patrick-beastmaster.tailf32530.ts.net/reserve/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 pbchrist-iconic-intelligence-reserve 'https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "pbchrist-iconic-intelligence-reserve": {
      "url": "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pbchrist-iconic-intelligence-reserve": {
      "type": "http",
      "url": "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.pbchrist-iconic-intelligence-reserve]
url = "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pbchrist-iconic-intelligence-reserve": {
      "type": "remote",
      "url": "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pbchrist-iconic-intelligence-reserve --url 'https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pbchrist-iconic-intelligence-reserve:
    url: "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "pbchrist-iconic-intelligence-reserve": {
      "Transport": "http",
      "Url": "https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add pbchrist-iconic-intelligence-reserve -t streamable-http -u 'https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp'
```

### Other

```json
{
  "mcpServers": {
    "pbchrist-iconic-intelligence-reserve": {
      "type": "http",
      "url": "https://patrick-beastmaster.tailf32530.ts.net/reserve/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.

### 2026-11-21 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 64, +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.

### 2026-11-16 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 61, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: ICONIC Intelligence Reserve — Free Agent Discovery and Assessment → ICONIC Intelligence Reserve — business memory and outcome ledger for agents
- [security] Tool “reserve_describe” rewrote its description, which is the text the model reads
- [security] Tool “reserve_offers” rewrote its description, which is the text the model reads
- [security] Tool “reserve_plans” rewrote its description, which is the text the model reads
- [security] Tool “reserve_quote” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 46 → 52
- [functional] New tool “reserve_pass_evaluate”
- [functional] New tool “reserve_pass_export”
- [functional] New tool “reserve_pass_recall”
- [functional] New tool “reserve_pass_record_action”
- [functional] New tool “reserve_pass_record_decision”
- [functional] New tool “reserve_pass_record_outcome”
- [functional] New tool “reserve_pass_remember”
- [functional] New tool “reserve_pass_status”
- [functional] New tool “reserve_pass_trace”
- [functional] New tool “reserve_pass_verify_outcome”

### 2026-11-12 (score 61, −6)

- [critical regression] Authorization: partial → fail
- [security] New tool “reserve_sandbox_release”, which the server declares destructive

### 2026-11-10 (score 67, +7)

- [security improvement] Authorization: unverified → partial
- [cosmetic] Tool “reserve_assess” changed its title: Assess
- [cosmetic] Tool “reserve_demo” changed its title: Demo
- [cosmetic] Tool “reserve_describe” changed its title: Describe
- [cosmetic] Tool “reserve_handoff” changed its title: Handoff
- [cosmetic] Tool “reserve_offers” changed its title: Offers
- [cosmetic] Tool “reserve_plans” changed its title: Plans
- [cosmetic] Tool “reserve_quote” changed its title: Quote
- [cosmetic] Tool “reserve_sandbox_evaluate” changed its title: Sandbox Evaluate
- [cosmetic] Tool “reserve_sandbox_recall” changed its title: Sandbox Recall
- [cosmetic] Tool “reserve_sandbox_record_action” changed its title: Sandbox Record Action
- [cosmetic] Tool “reserve_sandbox_record_decision” changed its title: Sandbox Record Decision
- [cosmetic] Tool “reserve_sandbox_record_outcome” changed its title: Sandbox Record Outcome
- [cosmetic] Tool “reserve_sandbox_remember” changed its title: Sandbox Remember
- [cosmetic] Tool “reserve_sandbox_start” changed its title: Sandbox Start
- [cosmetic] Tool “reserve_sandbox_trace” changed its title: Sandbox Trace
- [cosmetic] Tool “reserve_sandbox_verify_outcome” changed its title: Sandbox Verify Outcome

### 2026-11-09 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (27)

### `reserve_describe` (~29 tokens)

Describe

One-call discovery: offer catalog, the free quote, the paid Reserve Pass, tools and limits.

### `reserve_offers` (~31 tokens)

Offers

List offers: the free assessment, the paid self-serve Reserve Pass, and what is not on sale.

### `reserve_quote` (~40 tokens)

Quote

Get an exact quote: $0 assessment, the paid Reserve Pass with how to buy, or NOT_ON_SALE.

Input parameters:

- `offer_id` (string, required)

### `reserve_assess` (~79 tokens)

Assess

Free, stateless fit assessment and specific first outcome-linked workflow plan.

Input parameters:

- `business_type` (string, required)
- `existing_memory` (boolean)
- `measurable_outcome` (string, required)
- `problem` (string, required)
- `recurring_workflow` (string, required)
- `sensitive_data` (boolean)
- `systems` (array, required)

### `reserve_demo` (~21 tokens)

Demo

Run real Reserve operations on ephemeral synthetic data; no confidential inputs.

### `reserve_sandbox_start` (~20 tokens)

Sandbox Start

Create an isolated, one-hour fictional data sandbox.

### `reserve_sandbox_release` (~31 tokens)

Sandbox Release

Explicitly destroy your own fictional sandbox and free its capacity immediately.

Input parameters:

- `sandbox_key` (string, required)

### `reserve_sandbox_remember` (~45 tokens)

Sandbox Remember

Save a fictional observation in an expiring test Reserve.

Input parameters:

- `content` (string, required)
- `sandbox_key` (string, required)
- `source_ref` (string, required)

### `reserve_sandbox_recall` (~38 tokens)

Sandbox Recall

Retrieve fictional sandbox history using the genuine FTS5 engine.

Input parameters:

- `query` (string, required)
- `sandbox_key` (string, required)

### `reserve_sandbox_record_decision` (~58 tokens)

Sandbox Record Decision

Record a fictional recommendation linked to a synthetic subject.

Input parameters:

- `baseline` (string, required)
- `evidence_ids`
- `recommendation` (string, required)
- `sandbox_key` (string, required)
- `subject_ref` (string, required)

### `reserve_sandbox_record_action` (~52 tokens)

Sandbox Record Action

Attach a fictional observed action to a synthetic decision.

Input parameters:

- `decision_id` (string, required)
- `evidence_ref` (string, required)
- `sandbox_key` (string, required)
- `summary` (string, required)

### `reserve_sandbox_record_outcome` (~82 tokens)

Sandbox Record Outcome

Create a reported fictional outcome, with typed synthetic evidence.

Input parameters:

- `action_id` (string, required)
- `baseline_value`
- `evidence_kind` (string)
- `evidence_ref`
- `metric` (string, required)
- `metric_unit` (string, required)
- `metric_value` (number, required)
- `sandbox_key` (string, required)

### `reserve_sandbox_verify_outcome` (~45 tokens)

Sandbox Verify Outcome

Test separate reviewer credentials on fictional data only.

Input parameters:

- `evidence_ref` (string, required)
- `outcome_id` (string, required)
- `reviewer_key` (string, required)

### `reserve_sandbox_trace` (~36 tokens)

Sandbox Trace

Read the synthetic recommendation -> action -> outcome chain.

Input parameters:

- `sandbox_key` (string, required)
- `subject_ref` (string, required)

### `reserve_sandbox_evaluate` (~30 tokens)

Sandbox Evaluate

Inspect synthetic outcome changes, source coverage and missing data.

Input parameters:

- `sandbox_key` (string, required)

### `reserve_pass_status` (~33 tokens)

Pass Status

Paid Reserve Pass: expiry, days left and usage for your own private Reserve.

Input parameters:

- `reserve_key` (string, required)

### `reserve_pass_remember` (~57 tokens)

Pass Remember

Paid Reserve Pass: save a fact with its source to your persistent private Reserve.

Input parameters:

- `content` (string, required)
- `evidence_status` (string)
- `reserve_key` (string, required)
- `source_ref` (string, required)

### `reserve_pass_recall` (~47 tokens)

Pass Recall

Paid Reserve Pass: search what your Reserve remembers, across sessions and models.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `reserve_key` (string, required)

### `reserve_pass_record_decision` (~61 tokens)

Pass Record Decision

Paid Reserve Pass: record a recommendation and its baseline for one subject.

Input parameters:

- `baseline` (string, required)
- `evidence_ids`
- `recommendation` (string, required)
- `reserve_key` (string, required)
- `subject_ref` (string, required)

### `reserve_pass_record_action` (~63 tokens)

Pass Record Action

Paid Reserve Pass: record what was actually done about a decision (or not done).

Input parameters:

- `decision_id` (string, required)
- `evidence_ref`
- `reserve_key` (string, required)
- `status` (string)
- `summary` (string, required)

### `reserve_pass_record_outcome` (~96 tokens)

Pass Record Outcome

Paid Reserve Pass: record the measured result of an action, with its evidence kind.

Input parameters:

- `action_id` (string, required)
- `baseline_value`
- `confounders` (string)
- `evidence_kind` (string)
- `evidence_ref`
- `metric` (string, required)
- `metric_unit` (string, required)
- `metric_value` (number, required)
- `reserve_key` (string, required)

### `reserve_pass_verify_outcome` (~55 tokens)

Pass Verify Outcome

Paid Reserve Pass: a separate reviewer key (rsvr_...) attests a reported outcome.

Input parameters:

- `evidence_ref` (string, required)
- `outcome_id` (string, required)
- `reviewer_key` (string, required)

### `reserve_pass_trace` (~45 tokens)

Pass Trace

Paid Reserve Pass: the full decision, action and outcome chain for a subject.

Input parameters:

- `decision_id`
- `reserve_key` (string, required)
- `subject_ref`

### `reserve_pass_evaluate` (~45 tokens)

Pass Evaluate

Paid Reserve Pass: which recorded decisions worked, with deltas and missing data.

Input parameters:

- `metric`
- `reserve_key` (string, required)
- `subject_ref`

### `reserve_pass_export` (~45 tokens)

Pass Export

Paid Reserve Pass: export every record you own, 100 per page. Your data leaves with you.

Input parameters:

- `offset` (integer)
- `reserve_key` (string, required)

### `reserve_plans` (~31 tokens)

Plans

What is free, what is on sale now (Reserve Pass) and which larger plans are not yet sold.

### `reserve_handoff` (~24 tokens)

Handoff

Return approved human consultation and pilot-onboarding steps; no outreach is sent.

## Diagnostics

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

## Score history

- 2026-11-21: 65
- 2026-11-20: 64
- 2026-11-19: 64
- 2026-11-18: 63
- 2026-11-17: 63
- 2026-11-16: 63
- 2026-11-15: 62
- 2026-11-14: 62
- 2026-11-13: 61
- 2026-11-12: 61
- 2026-11-11: 67
- 2026-11-10: 67
- 2026-11-09: 60
- 2026-11-08: 59
- 2026-11-07: 59
- 2026-11-06: 58
- 2026-11-05: 4

## Common questions

### What is the ICONIC Intelligence Reserve — Free Agent Assessment MCP server?

ICONIC Intelligence Reserve — Free Agent Assessment is an MCP server listed in the public MCP registry as io.github.pbchrist/iconic-intelligence-reserve. Free agent assessment and a one-hour synthetic Reserve sandbox with outcome tracing. This page covers its hosted endpoint (https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp).

### Is the ICONIC Intelligence Reserve — Free Agent Assessment MCP server safe to use?

ICONIC Intelligence Reserve — Free Agent Assessment scores 65 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 ICONIC Intelligence Reserve — Free Agent Assessment MCP server expose?

ICONIC Intelligence Reserve — Free Agent Assessment exposes 27 tools: reserve_describe, reserve_offers, reserve_quote, reserve_assess, reserve_demo, and 22 more. Their descriptions and schemas cost roughly 1,239 tokens of context every time the server is loaded.

### Does the ICONIC Intelligence Reserve — Free Agent Assessment MCP server require authentication?

No. We connected to ICONIC Intelligence Reserve — Free Agent Assessment without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ICONIC Intelligence Reserve — Free Agent Assessment MCP server still maintained?

ICONIC Intelligence Reserve — Free Agent Assessment is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the ICONIC Intelligence Reserve — Free Agent Assessment MCP server?

VerifyMCP ran 13 checks on ICONIC Intelligence Reserve — Free Agent Assessment, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://patrick-beastmaster.tailf32530.ts.net/reserve/mcp
- Website: https://iconic.onl/agents/reserve/
- Changelog RSS feed: https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp.json
- HTML version of this page: https://verifymcp.io/servers/pbchrist-iconic-intelligence-reserve/reserve-mcp
