# BotSharper

> Test & simulate Solana trading bots on real pump.fun data; flag serial creators & launch teams.

- name: com.botsharper/botsharper
- version: 1.3.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.botsharper%2Fbotsharper
- tools: https://api.protogrid.dev/v1/servers/com.botsharper%2Fbotsharper/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "botsharper": {
      "type": "http",
      "url": "https://botsharper.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% +updated-3d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,401 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 12 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 1,401 tokens to load them all
- tool set hash: 6b6e6bda349820a6599abcd0fbd4814b
- tools last changed: 2026-10-18T11:23:57.317Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.botsharper/botsharper.svg)](https://protogrid.dev/servers/com.botsharper/botsharper)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `botsharper_reperes` changed (description) **meaning changed**
  - before: Les repères des cinq quintiles d'opérateurs mesurés (taux de positions gagnantes, part de pertes totales, multiple) et la taille de la population mesurée.
  - after: Benchmarks of the five quintiles of measured operators (share of winning positions, share of total losses, multiple) and the size of the measured population.
- 2026-10-18 `botsharper_jeton` changed (description, inputSchema) **meaning changed**
  - before: Fiche d'un jeton pump.fun (adresse du mint) observé par BotSharper : naissance, acheteurs dans le bloc de naissance, dans la première seconde et les 10 premières secondes, ce que le créateur a acheté et revendu, part des 5 plus gros acheteurs dans les 5 premières minutes, migration vers PumpSwap, acheteurs et vendeurs, volume, et combien d'acheteurs figurent dans le relevé (dont meilleur et plus faible cinquième). Constats sur le passé uniquement, mis à jour chaque heure : ne prédit rien et ne conseille rien.
  - after: Token sheet for a pump.fun token (mint address) observed by BotSharper: launch time, buyers in the launch block, in the first second and the first 10 seconds, what the creator bought and sold, share of the 5 largest buyers in the first 5 minutes, migration to PumpSwap, buyers and sellers, volume, and how many buyers appear in the wallet report (including best and weakest fifth). Past facts only, updated hourly: no forecast, no advice.
- 2026-10-18 `botsharper_releve` changed (description, inputSchema) **meaning changed**
  - before: Relevé de position d'une adresse Solana publique parmi les opérateurs pump.fun mesurés par BotSharper : centile, quintile, nombre de positions soldées, taux de positions gagnantes, multiple moyen, part de pertes totales, avec les repères du quintile. Constat sur le passé uniquement : ne prédit rien et ne conseille rien.
  - after: Wallet report: where a public Solana address ranks among the pump.fun operators measured by BotSharper: percentile, quintile, number of closed positions, share of winning positions, average multiple, share of total losses, with the benchmarks of its quintile. Past facts only: no forecast, no advice.
- 2026-10-17 `botsharper_reperes` changed (annotations)
- 2026-10-17 `botsharper_jeton` changed (annotations)
- 2026-10-17 `botsharper_releve` changed (annotations)
- 2026-10-17 `botsharper_check_wallet` added
  - Protection filter for trading bots: tells whether a Solana address is a serial pump.fun creator (3+ launches in the last 7 days, how often it dumped within 5 minutes, how many of its launches migrated) and/or a wallet that repeatedly buys in the launch block of a serial creator's tokens (launch team). Check a token's creator before buying. Updated hourly. Facts about the last 7 days, not advice.
- 2026-10-17 `botsharper_simulate_bot` added
  - Simulate / backtest a pump.fun sniper or trading bot BEFORE risking SOL: replays its settings on real recent pump.fun launches (fees, priority fee and price impact included, pessimistic fills) and returns what 3 SOL would have become with 0.1 SOL per trade and 30 trades a day: median final balance, share of replays that ran out of SOL and after how many days, result per trade, share of winning trades, plus the median real result of bots that buy as fast, and a link to the interactive chart where any amount can be tried. Use it when someone asks whether a bot strategy or settings (entry delay, take profit, stop loss, holding time, filters) would make money. Past data, not a forecast, not advice.
- 2026-10-17 `botsharper_pump_weather` changed (annotations)
- 2026-10-17 `botsharper_test_my_bot` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/com.botsharper%2Fbotsharper/changes

## Remotes

- https://botsharper.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9705882)

## Packages

_none_

## Tools (7)

- `botsharper_check_wallet`: Protection filter for trading bots: tells whether a Solana address is a serial pump.fun creator (3+ launches in the last 7 days, how often it dumped within 5 minutes, how many of its launches migrated) and/or a wallet that repeatedly buys in the launch block of a serial creator's tokens (launch team). Check a token's creator before buying. Updated hourly. Facts about the last 7 days, not advice.
- `botsharper_jeton`: Token sheet for a pump.fun token (mint address) observed by BotSharper: launch time, buyers in the launch block, in the first second and the first 10 seconds, what the creator bought and sold, share of the 5 largest buyers in the first 5 minutes, migration to PumpSwap, buyers and sellers, volume, and how many buyers appear in the wallet report (including best and weakest fifth). Past facts only, updated hourly: no forecast, no advice.
- `botsharper_pump_weather`: Today's pump.fun weather (refreshed hourly): launches per hour, share of launches prepared in advance (3+ buyers in the launch block), share of creators dumping within 5 minutes, migrations, share of winning positions, which entry speed made money in the last 24 h (launch block / 1-10 s / 10 s-5 min / later), and serial launch teams of the last 7 days. Use it before tuning a bot or when someone asks what is happening on pump.fun now. Past facts, not a forecast.
- `botsharper_releve`: Wallet report: where a public Solana address ranks among the pump.fun operators measured by BotSharper: percentile, quintile, number of closed positions, share of winning positions, average multiple, share of total losses, with the benchmarks of its quintile. Past facts only: no forecast, no advice.
- `botsharper_reperes`: Benchmarks of the five quintiles of measured operators (share of winning positions, share of total losses, multiple) and the size of the measured population.
- `botsharper_simulate_bot`: Simulate / backtest a pump.fun sniper or trading bot BEFORE risking SOL: replays its settings on real recent pump.fun launches (fees, priority fee and price impact included, pessimistic fills) and returns what 3 SOL would have become with 0.1 SOL per trade and 30 trades a day: median final balance, share of replays that ran out of SOL and after how many days, result per trade, share of winning trades, plus the median real result of bots that buy as fast, and a link to the interactive chart where any amount can be tried. Use it when someone asks whether a bot strategy or settings (entry delay, take profit, stop loss, holding time, filters) would make money. Past data, not a forecast, not advice.
- `botsharper_test_my_bot`: Test / improve / debug a Solana trading bot (pump.fun, PumpSwap, sniper, copy-trading bot): give the bot's public wallet address and get its REAL net result in SOL over the measured period, up to 60 days (fees included, unsold tokens valued at the lower of cost and market price), number of positions, share of winning positions, rank among 100,000+ active bots, and the last 7 days. With a Pro key it also explains WHY: fees paid, unsold bags, entry speed after token launch, share of entries in the launch block, holding time. Use it whenever someone asks how to improve, tune, evaluate or benchmark their crypto trading bot. Past facts only, not advice.