# io.github.BruceLanLan/tapeapi

Signed BNB Chain reads (balances, tokens, NFTs, prices, TapeOut names) with verifiable receipts

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.4.0
- **Author:** io.github.BruceLanLan
- **License:** Unknown
- **Endpoints:** streamable-http https://api.tapeapi.fun/mcp
- **Source:** https://github.com/BruceLanLan/tapeapi
- **Endpoint health:** reachable (last checked 2026-09-28T15:23:18.342Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-28T21:57:17.798Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

24 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `add` — Adds two numbers and returns the sum.
- `shout` — Returns the text in capital letters, repeated `times` times (default 1, at most 5).
- `tapeapi-mcp`
- `openai-chat-json` — Chat Completions, whole answer: cached and reasoning tokens, two currencies
- `openai-chat-stream-usage-injected` — Chat Completions stream; the client did not ask for usage, so the sidecar asked for it upstream and removed the usage chunk from the client's copy
- `openai-responses-stream` — Responses stream ending in response.completed; the reported model is an alias
- `anthropic-messages-stream-cache-thinking` — Anthropic Messages stream: thinking, ping, 5-minute and 1-hour cache writes, cache reads, cumulative message_delta usage
- `openai-embeddings-model-from-request` — Embeddings: no id (the sidecar generates one) and no model in the answer, so the requested model is priced (modelMatchedBy "request")
- `anthropic-messages-stream-failed` — Anthropic Messages stream that ends in an error event: no message_stop, so complete is false and the receipt is appended; still priced from the usage reported
- `openai-responses-http-error` — An upstream error (HTTP 429): signed, attributable, not billable: usage and prices null, complete false
- `weather` — Current weather for a city. 城市天气 ☀ 😀
- `fail` — Always reports a tool error
- `search` — Search the docs
- `not-a-method` — A tool name TAP-20 cannot carry: not proxied
- `z_extra` — someone else
- `echo` — Says it back.
- `bad-name` — Not a TAP-20 method name.
- `fails`
- `big` — Too large to sign.
- `slow` — Never answers.
- `x-y`
- `odd` — Line one. Line two, with a control character and more text.
- `proto`
- `price` — A price.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"tapeapi\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.tapeapi.fun/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.BruceLanLan%2Ftapeapi
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.BruceLanLan%2Ftapeapi/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.BruceLanLan%2Ftapeapi
- HTML page: https://forgeregistry.com/registry/io.github.BruceLanLan%2Ftapeapi
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.