# `io.github.ysgjay/token-command-center` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.ysgjay/token-command-center
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.ysgjay/token-command-center
- Version: 0.3.0 (active)
- Publisher: io.github.ysgjay (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:52:03.851Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Token Command Center
Free token data: revenue, net flow after emissions, supply/unlock history, catalysts, errors marked
```

Scanned 2026-11-21T06:17:57.960Z over streamable-http.

**18 tools: 9 change things and 9 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 9 | ask |
| Only reads | read | 9 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__token-command-center__tc_get_token_digest` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

- **warn** Annotations that disagree with the tool in `tc_moves` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "tc_moves" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "tc_moves" says "move": a word for a change.
```


## Changes things (9)

Creates or changes something that can be changed back. Claude Code: ask.

### `tc_alerts`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Recent threshold alerts (revenue deterioration, emission acceleration, unlock cliffs, flow flips).
```

### `tc_brief`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
The whole Book in about 1.5 KB: freshness and caveats, verdict and lens mix, biggest 30-day revenue movers, highest health, latest high alerts, plus a plain-text version. Use for market-wide questions.
```

### `tc_calendar`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Upcoming dated catalysts (unlocks, emission steps, votes, launches) across the Book, soonest first, at most 20. Optional token slug, tokens (several slugs), kind and horizon in days (default 30, max 180). Text is analyst notes; each event also has symbol, kind, estimated (date marked approximate), a plain title with title_source (curated: hand-written for this note; measured: from the measured unlock size; note: cut from the note), and the measured next unlock (pct_circ, pct_supply, tokens, source, as_of; CoinMarketCap) when it falls within a day of the event, else null. Events whose text starts 'Scheduled unlock' come from the measured schedule alone, fill only slots the analyst events leave free, and are counted in scheduled_total.
```

### `tc_categories`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Token counts per category.
```

### `tc_ledger`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Prediction ledger tallies: open and graded call counts, next grading date, calls by side. Counts only; individual calls are not published.
```

### `tc_moves`

- The name "tc_moves" says "move": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Biggest movers: kind=movers ranks 30-day revenue change against price change (divergence); kind=momentum ranks a 14-day composite of revenue, net-flow yield and health changes. Up to 8 up and 8 down. Rows marked base_effect started from almost zero.
```

### `tc_projects`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Revenue-earning projects with NO token (wallets, trading bots, apps, launchpads, stablecoin issuers, listed companies): yearly revenue on the 30-day pace, last 12 months, 30-day change, category, chains, token_status (none, points, announced, public_equity with a stock ticker, launched). Figures only, no health score. Use with tc_screen to rank apps and tokens together in a category. Source DefiLlama, with link and date; rows with flags need a caveat.
```

### `tc_screen`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Screen the whole Book (all scored tokens) and get compact ranked rows. Filters: lens (long, short, no-edge), verdict (Real, Mid, Theater), tier, category, sector (a clean label such as Lending or Memes), flow_model (comma-separated for several), stale, query; numeric ranges via min/max objects, e.g. {"min": {"health": 60, "arr": 1000000}, "max": {"ps": 20}}. Fields: alerts, arr (annualized revenue, USD), arr_30d (ARR change over 30 days, %), arr_7d (ARR change over 7 days, %), category, conflicts, date, fdv, flow_model, health (0-100 health score, set when the scorecard is written), health_change, holders_rev (annualized revenue to holders, USD), lens (long, short or no-edge), mcap, name, net_flow (holders revenue minus emissions, USD/yr), nf_yield (net flow / market cap, %), pct_unlocked, price, price_frozen_days, ps (market cap / annualized revenue), scorecard_age_days, sector (one clean sector beside the raw category, or null), stale, symbol, tier, unlock_30d (% of supply unlocking in the next 30 days), verdict (value accrual: Real, Mid or Theater). Tokens with no value for a ranged field are excluded, never counted as zero.
```

### `tc_series`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
One token's history as chartable series from TCC's daily snapshots (since 2026-06-09). Each metric returns `summary` {first, last, change_pct, min, max} first — answer trend questions from it — then at most 60 points (weekly by default). Frozen price feeds are null, not flat. Metrics: price, mcap, fdv, ann_fees, ann_revenue, ann_holders_rev, net_flow_usd, ps_ratio, health_score, ann_emissions_usd, circ_supply, total_supply, pct_unlocked, daily_fees, daily_revenue, daily_holders_rev, price_llama (daily_* and price_llama are DefiLlama, years deep; the rest are TCC snapshots).
```

## Only reads (9)

Looks things up and changes nothing. Claude Code: allow.

### `tc_compare`

- The name "tc_compare" says "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Two to six tokens side by side: price, valuation, revenue and its 7/30-day change, revenue_figures per token (30-day annualized pace and real last-12-months revenue, P/S on both), holders revenue, net-flow yield, P/S, unlocks, health with six pillar scores, verdict, lens, and any frozen-price or old-scorecard flags. Accepts slugs or unambiguous symbols.
```

### `tc_get_project`

- The name "tc_get_project" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
One coinless project by slug (from tc_projects): revenue figures, products, chains, token_status, source link and date.
```

### `tc_get_report`

- The name "tc_get_report" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Newest markdown scorecard for a slug (clipped). Long; prefer tc_get_token unless the user asks for the write-up.
```

### `tc_get_token`

- The name "tc_get_token" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
One token's full scorecard (about 8 KB): six pillar scores, the stat grid with a provenance tag per figure, ARR change over 1D/7D/30D/1Y, 30-point history, revenue basis, analyst facts, lens, links, gaps, and this token's alerts and source conflicts. Use only when tc_get_token_digest lacks what the user asked for.
```

### `tc_get_token_digest`

- The name "tc_get_token_digest" says "get": a word for reading.
- Tag private-data: The description's first sentence says "note": it reads notes.

Description, as the server wrote it:

```untrusted-server-text
One token in about 2 KB: latest price, valuation, revenue and flows, 7- and 30-day changes, revenue_figures (the 30-day annualized pace AND the real last-12-months revenue, P/S on both, one-line notes on how each is formed), health score with its six pillar scores and verdict, supply unlocks, lens, and data-quality counts. Prefer this over tc_get_token.
```

### `tc_list_tokens`

- The name "tc_list_tokens" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Page through scored tokens with optional filters. Sorts: health, mcap, revenue, net_flow, ps, unlock_30d, alerts, name.
```

### `tc_resolve`

- The name "tc_resolve" says "resolve": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Turn a symbol, $cashtag, name or slug into Token Command Center slugs. Returns exact (one slug) or ambiguous=true with every candidate when tokens share a symbol (e.g. POL); never guess between them. Call before a digest when the user names a token.
```

### `tc_search_tokens`

- The name "tc_search_tokens" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Find slugs by symbol or name before calling tc_get_token_digest.
```

### `tc_status`

- The name "tc_status" says "status": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Freshness, size and source-agreement stats of the token universe. Call first; quote generated_at.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `token-command-center`:

```json
{
  "permissions": {
    "allow": [
      "mcp__token-command-center__tc_status",
      "mcp__token-command-center__tc_list_tokens",
      "mcp__token-command-center__tc_get_token",
      "mcp__token-command-center__tc_get_token_digest",
      "mcp__token-command-center__tc_search_tokens",
      "mcp__token-command-center__tc_resolve",
      "mcp__token-command-center__tc_compare",
      "mcp__token-command-center__tc_get_report",
      "mcp__token-command-center__tc_get_project"
    ],
    "ask": [
      "mcp__token-command-center__tc_alerts",
      "mcp__token-command-center__tc_categories",
      "mcp__token-command-center__tc_screen",
      "mcp__token-command-center__tc_brief",
      "mcp__token-command-center__tc_series",
      "mcp__token-command-center__tc_calendar",
      "mcp__token-command-center__tc_moves",
      "mcp__token-command-center__tc_ledger",
      "mcp__token-command-center__tc_projects"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__token-command-center__tc_get_token_digest`: private-data

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:13:15.435Z, unchanged since 2026-11-06T05:10:37.222Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `9` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.

https://token-command-center-gamma.vercel.app/mcp: tools/list returned 18 tools to an anonymous client, including tc_alerts (write), tc_categories (write), tc_screen (write), tc_brief (write), tc_series (write) and 4 more
```

Posture changes:

- 2026-11-06T05:10:37.222Z: Tools that change things, listed without credentials `8` -> `9`
