mcp-coreCAUTION
Shared foundation for building MCP servers -- Streamable HTTP transport, OAuth 2.1, browser-based credential setup, and a shared embedding daemon.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Shared foundation for building MCP servers -- Streamable HTTP transport, OAuth 2.1, browser-based credential setup, and a shared embedding daemon.
[](https://github.com/n24q02m/mcp-core/actions/workflows/ci.yml) [](https://codecov.io/gh/n24q02m/mcp-core) [](https://pypi.org/project/n24q02m-mcp-core/) [](https://www.npmjs.com/package/@n24q02m/mcp-core) [](LICENSE)
[](#) [](#) [](https://github.com/python-semantic-release/python-semantic-release) [](https://developer.mend.io/)
Sister projects from n24q02m (click to expand)
d545ba741633OBSERVED · 2026-10-12Connect
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 mcp add mcp-core --env CREDENTIAL_SECRET=${CREDENTIAL_SECRET} --env MCP_AUTH_DISABLE=${MCP_AUTH_DISABLE} --env MCP_D1_TOKEN=${MCP_D1_TOKEN} --env MCP_JWT_SIGNING_SECRET=${MCP_JWT_SIGNING_SECRET} -- npx -y @n24q02m/[email protected]{
"mcpServers": {
"mcp-core": {
"command": "npx",
"args": [
"-y",
"@n24q02m/[email protected]"
],
"env": {
"CREDENTIAL_SECRET": "${CREDENTIAL_SECRET}",
"MCP_AUTH_DISABLE": "${MCP_AUTH_DISABLE}",
"MCP_D1_TOKEN": "${MCP_D1_TOKEN}",
"MCP_JWT_SIGNING_SECRET": "${MCP_JWT_SIGNING_SECRET}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
config__open_relay | read | try: |
hello | read | return |
Trust audit
CAUTIONgrade D · trust 63/100 Install with care. The audit found things worth knowing before you trust its output.
| 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 (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
url = f"http://127.0.0.1:{port}/setup?token={token}"secret = "test-credential-secret-value"
SECRET = "test-credential-secret-value"
const SECRET = 'stable-sub-test-secret'
const SECRET = 'test-credential-secret-value'
const SECRET = 'test-credential-secret-value'
"CI_APP_KEY": "-----BEGIN RSA PRIVATE KEY-----\nfoo\n-----END",
.coderabbit.yaml
.gitleaks.toml
.infisical.json
.mise.toml
.pre-commit-config.yaml
cp ../../README.md .
cp ../../README.md .
_cred_path("plugin", "../../evil")b.put("wet/subs/u1/tokens/../../escape", b"x")malicious_name = "../../etc/passwd"
"169.254.169.254", # link-local (cloud metadata)
middleware = [OAuthMiddleware(issuer=issuer, resource_metadata_url="http://127.0.0.1:9876/.well-known/oauth-protected-resource")]
resourceMetadataUrl: 'http://127.0.0.1:9876/.well-known/oauth-protected-resource'
"redirect_uri": "http://127.0.0.1:5555/callback",
meta = authorization_server_metadata("http://127.0.0.1:9876")ciphertext = base64.b64decode(result["ciphertext"])
iv = base64.b64decode(result["iv"])
tag = base64.b64decode(result["tag"])
Gates applied: no_behavioural_pass.
d545ba741633full audit observations/trust-audit/mcp-server/n24q02m__mcp-core.json · Report an issue / request a re-scanAudit 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 |
|---|---|---|---|---|---|
| 2026-10-12 | d545ba741633 | CAUTION | D | 63 | first audit |
Questions
What is the @n24q02m/mcp-core MCP server?
Shared foundation for building MCP servers -- Streamable HTTP transport, OAuth 2.1, browser-based credential setup, and a shared embedding daemon.
What tools does @n24q02m/mcp-core expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @n24q02m/mcp-core safe to connect to an agent?
With care. The audit graded it D (63/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does @n24q02m/mcp-core need?
It reads CREDENTIAL_SECRET, MCP_AUTH_DISABLE, MCP_D1_TOKEN, MCP_JWT_SIGNING_SECRET, MCP_KV_TOKEN, MCP_MY_SERVER_API_KEY, MCP_RELAY_PASSWORD, MCP_TELEGRAM_BOT_TOKEN and MCP_VECTORIZE_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 @n24q02m/mcp-core run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @n24q02m/mcp-core at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (d545ba741633), read on 2026-10-12. The repository is watched and re-audited when it changes.