Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ryan-haver/fusebase-mcp --skill api-explorationgit clone --depth 1 https://github.com/ryan-haver/fusebase-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration)<a href="https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/api-exploration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ryan-haver/fusebase-mcp/api-exploration"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/api-exploration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.00761 |
| Opus 5.5 | $0.00032 | $0.00304 |
| Sonnet 5.5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
api-exploration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to api-exploration — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Exploration with Temporary Tokens
When you're unsure about an API endpoint's behavior, response shape, or want to test a flow before committing to implementation — create a temporary token and run test calls directly.
Workflow
1. Create a temporary token
fusebase token create --app <appId>
This outputs a short-lived token (15 min) to stdout. Capture it:
TOKEN=$(fusebase token create --app <appId>)
The appId comes from fusebase.json → apps[].id.
2. Write and run test code
Create a temporary script (e.g. _test-api.ts) to make the API calls you want to verify:
const token = process.env.TOKEN || "<paste-token-here>";
const res = await fetch("https://api-endpoint/...", {
headers: { "x-app-feature-token": token },
});
console.log(res.status);
console.log(await res.json());
Run it:
TOKEN=$(fusebase token create --app <appId>) bun _test-api.ts
3. Inspect results and iterate
Read the output, adjust your calls, and re-run. Once you understand the API behavior, implement it properly in your app code.
4. Clean up
Delete the temporary test script when done — don't commit it.
Example: Testing @fusebase/dashboard-service-sdk
Use this to verify SDK calls before wiring them into app UI code.
_test-sdk.ts:
import {
createClient,
DatabasesApi,
CustomDashboardRowsApi,
} from "@fusebase/dashboard-service-sdk";
const token = process.env.TOKEN!;
const BASE_URL =
"https://app-api.thefusebase.com/v4/api/proxy/dashboard-service/v1";
const client = createClient({
baseUrl: BASE_URL,
defaultHeaders: { "x-app-feature-token": token },
});
const dbApi = new DatabasesApi(client);
const rowsApi = new CustomDashboardRowsApi(client);
// List databases visible to this app
const dbs = await dbApi.listDatabases({});
console.log("databases:", JSON.stringify(dbs, null, 2));
// Read rows from a specific dashboard view
const rows = await rowsApi.getRows({
dashboardId: "<dashboardId>",
viewId: "<viewId>",
});
console.log("rows:", JSON.stringify(rows, null, 2));
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 105 lines · 79 tokens per session scan A f93ed335be2c
api-exploration is a skill published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 761 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to api-exploration, differing in 2 lines, and is treated as a copy.
api-exploration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| api-explorationryan-haver/fusebase-mcp | Skill | 8 | 3d ago | MIT | A | 79 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | today | MIT | A | 106 | Claude Code |