ai_agents_api_librarySAFE
mcp/eater2/ai-agents-api-library
Verified catalog of 300+ APIs and MCP servers that AI agents can call after a one-time API key/OAuth setup. JSON, llms.txt and an MCP server for agents.
Verdict
SAFE
Grade
B
Trust score
87 /100
Exposed tools
4 4r · 0w · 0d
Transport
stdio · streamable-http
License
NOASSERTION
Stars
1
01
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Polski · HTML · llms.txt · catalog.json
Read from source at commit
761ded2fa837OBSERVED · 2026-10-1102
Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude-code (npm)
claude mcp add ai-agents-api-library -- npx -y [email protected]
03
Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_api | read | |
get_reviews | read | |
list_categories | read | |
search_apis | read |
04
Trust audit
SAFEgrade B · trust 87/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (7 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
MEDIUMObfuscation / stealth · obf.zero_width · CWE-506, CWE-94
catalog/reviews/slack-api.json:170
"pros": "This platform has been one of the best for my work environment, due to the ease with which I can communicate with my entire work team. In our company, we have different work areas, since we a
LOWInventory / provenance · inv.binary · CWE-1104
docs/ai-agents-api-library-skill.zip
ai-agents-api-library-skill.zip
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWInventory / provenance · inv.hidden_file · CWE-1104
docs/.nojekyll
.nojekyll
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/build.py:811
f'<header class="top"><div class="in"><a class="brand" href="../../">{e_(TITLE)}<small>{e_(c["en"])}</small></a>',LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/build.py:812
f'<nav class="tabs"><a href="../../">All categories</a><a href="{RAW}catalog/{c["id"]}.json">JSON</a>'LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/build.py:813
f'<a href="../../llms.txt">llms.txt</a><a href="{GH}">GitHub</a></nav></div></header><main>',LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/http.test.mjs:26
url = `http://127.0.0.1:${http.address().port}/mcp`;LOWObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
README.md:5
<a href="https://registry.modelcontextprotocol.io/v0/servers?search=io.github.eater2/ai-agents-api-library"><img alt="Official MCP Registry" src="https://img.shields.io/badge/MCP_Registry-io.github.ea
LOWObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
README.pl.md:5
<a href="https://registry.modelcontextprotocol.io/v0/servers?search=io.github.eater2/ai-agents-api-library"><img alt="Official MCP Registry" src="https://img.shields.io/badge/MCP_Registry-io.github.ea
LOWObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
docs/index.html:53
<p class="badges"><a href="https://registry.modelcontextprotocol.io/v0/servers?search=io.github.eater2/ai-agents-api-library"><img alt="Official MCP Registry" src="https://img.shields.io/badge/MCP_Reg
LOWObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
docs/pl/index.html:50
<p class="badges"><a href="https://registry.modelcontextprotocol.io/v0/servers?search=io.github.eater2/ai-agents-api-library"><img alt="Official MCP Registry" src="https://img.shields.io/badge/MCP_Reg
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:108
| [Linkup](https://www.linkup.so)<br>[](https://smithery.ai/servers/LinkupPlatform/linkup-mcp-server) | Lets an agent searc
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:111
| [Perplexity Sonar / Search API](https://docs.perplexity.ai) | Lets an agent call Perplexity's Search API or MCP tools (search/ask/research/reason) for real-time grounded web answers. | API key / OAu
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:151
| [Congress.gov API](https://www.congress.gov/)<br>[](https://github.com/
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:193
| [D-ID API](https://www.d-id.com) | Animate photos into talking-head videos with lip-sync from text or audio via REST API. | API key | [✅](https://docs.d-id.com/mcp) | Trial: 14 days with 3 minutes o
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:197
| [Kling AI API](https://klingai.com)<br>[](https://github.com/199-mcp/mcp-kling) | Ge
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
INFOInventory / provenance · inv.oversize · CWE-1104
catalog/all.json
catalog/all.json
Why it matters. 1448820 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
docs/catalog.json
docs/catalog.json
Why it matters. 1448820 bytes not read
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
docs/c/finance-payments/index.html:70
<tr id="wise-api"><td><a href="https://docs.wise.com/api-docs"><b>Wise API</b></a></td><td>Send international transfers, check exchange rates, and manage multi-currency balances via REST API.</td><td>
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
docs/llms-full.txt:698
- [FREE] Wise API | Send international transfers, check exchange rates, and manage multi-currency balances via REST API. | auth:api_key+oauth2 (Authorization: Bearer <API token> (personal, Wise busine
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
llms-full.txt:698
- [FREE] Wise API | Send international transfers, check exchange rates, and manage multi-currency balances via REST API. | auth:api_key+oauth2 (Authorization: Bearer <API token> (personal, Wise busine
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
data/enrich/corrections.md:13
- `mongodb-atlas`: auth_hint: MongoDB now recommends service accounts (OAuth2 client credentials, Bearer access token); HTTP Digest API keys are legacy
Why it matters. asks the agent to read credentials
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/c/cloud-hosting/index.html:55
<tr id="aws-apis"><td><a href="https://docs.aws.amazon.com/general/latest/gr/aws-apis-references.html"><b>AWS APIs</b></a></td><td>An agent can provision and control thousands of AWS resources (comput
Why it matters. asks the agent to read credentials
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/c/music-generation/index.html:58
<tr id="mubert-api"><td><a href="https://mubert.com/api"><b>Mubert API</b></a></td><td>Generate streaming or file-based background music from text/image prompts via REST/WebRTC API, 15s-25min tracks.<
Why it matters. asks the agent to read credentials
Gates applied: no_behavioural_pass.
Audited 2026-10-11 · audit v0.4.1 · source sha
761ded2fa837full audit observations/trust-audit/mcp-server/eater2__ai_agents_api_library.json · Report an issue / request a re-scan05
Audit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 761ded2fa837 | SAFE | B | 87 | first audit |
06
Questions
What is the ai_agents_api_library MCP server?
Verified catalog of 300+ APIs and MCP servers that AI agents can call after a one-time API key/OAuth setup. JSON, llms.txt and an MCP server for agents.
What tools does ai_agents_api_library expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is ai_agents_api_library safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (87/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does ai_agents_api_library need?
It reads GITHUB_PERSONAL_ACCESS_TOKEN, GITHUB_TOKEN, OPENROUTER_API_KEY and OPENROUTER_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does ai_agents_api_library run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as ai-agents-api-library at 0.3.7.
How current is this page?
The grade is for one exact copy of the source (761ded2fa837), read on 2026-10-11. The repository is watched and re-audited when it changes.