Skills
librarium
by jkudish
Send one research question to many search and AI sources and keep every answer with its citations and cost. CLI, MCP server and library.
Our verdict
We have not reviewed librarium yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About librarium
Send one research question to many search and AI sources and keep every answer with its citations and cost. CLI, MCP server and library.
Best for
Developers and researchers who need fast, multi-source search aggregation from the terminal.
Use cases
- Run parallel searches across multiple search engines and AI providers
- Aggregate research results from diverse sources into one view
- Automate deep research workflows in terminal-based pipelines
Notes
138 stars on GitHub. Last updated 2026-11-03. Licensed MIT.
Indexed from github-skill-md. Verified against the live GitHub repo.
Pros
- Parallel execution speeds up multi-source research
- Supports multiple providers for broader coverage
- Simple CLI interface fits into existing developer workflows
Cons
- Requires API keys for each provider, increasing setup overhead
- Output aggregation may lack deduplication or ranking
- Limited to command-line usage, not a GUI or library
Key facts
What we have checked
- Days since the last commit
- 0
- GitHub forks
- 3
- GitHub stars
- 138
- Days to a first reply on issues
- 0.6
- Open issues
- 2
- Releases in the last 90 days
- 2
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How librarium is growing
136 to 138
Health and security
Is librarium looked after, and what do its setup files show
Health score
77 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 0 days ago |
| Releases | 11.3 of 15 | 2 releases in 90 days |
| Issue replies | 20 of 20 | First reply in 0.6 days (median) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
37 out of 100
- Critical proxy-addr vulnerable to IP spoofing via IPv4-mapped IPv6 trust subnet (affects proxy-addr 2.0.7, pinned in package-lock.json).
- High MCP TypeScript SDK: Experimental tasks were not tied to the session that created them (affects @modelcontextprotocol/sdk 1.30.0, pinned in package-lock.json).
- High MCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation (affects @modelcontextprotocol/sdk 1.30.0, pinned in package-lock.json).
- High MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server (affects @modelcontextprotocol/sdk 1.30.0, pinned in package-lock.json).
- High body-parser vulnerable to Denial of Service via trailing bytes after a compressed request body (affects body-parser 2.3.0, pinned in package-lock.json).
- High sharp: Vulnerabilities in libheif: GHSA-g89c-p67h-r497 and GHSA-2jg2-4ch7-h545 (affects sharp 0.35.2, pinned in package-lock.json).
- High sharp : Vulnerability in librsvg dependency CVE-2026-96889 (affects sharp 0.35.2, pinned in package-lock.json).
- High source-map-js allows event-loop denial of service through indexed source-map section offsets (affects source-map-js 1.2.1, pinned in package-lock.json).
- High undici vulnerable to Denial of Service via unrequested WebSocket subprotocol (affects undici 7.29.0, pinned in package-lock.json).
- High undici vulnerable to TLS certificate validation bypass via dropped connect options in BalancedPool (affects undici 7.29.0, pinned in package-lock.json).
- High undici vulnerable to Denial of Service via unhandled error on excessive content-encodings (affects undici 7.29.0, pinned in package-lock.json).
- High launch-editor: `fs.existsSync()` existence check can be bypassed on Windows (affects vite 8.2.1, pinned in package-lock.json).
- High Zod can exhaust memory while validating oversized constrained collections (affects zod 4.4.3, pinned in package-lock.json).
- Medium MCP TypeScript client SDK: HTTP client transports and OAuth requests followed cross-origin redirects and re-sent custom headers and request bodies (affects @modelcontextprotocol/sdk 1.30.0, pinned in package-lock.json).
- Medium MCP TypeScript SDK: Server bearer authentication accepted tokens issued for another service (affects @modelcontextprotocol/sdk 1.30.0, pinned in package-lock.json).
- Medium Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock (affects @vitest/mocker 4.1.10, pinned in package-lock.json).
- Medium Vitest: Code injection via unauthenticated manual mock registration (affects @vitest/mocker 4.1.10, pinned in package-lock.json).
- Medium fast-uri vulnerable to inconsistent host case normalization via percent-encoded octets (affects fast-uri 3.1.7, pinned in package-lock.json).
- Medium fast-uri vulnerable to URI scheme spoofing via percent-encoded scheme decoding (affects fast-uri 3.1.7, pinned in package-lock.json).
- Medium fast-uri vulnerable to host confusion via unchecked WHATWG host canonicalization (affects fast-uri 3.1.7, pinned in package-lock.json).
- Medium Hono: `serveStatic` decodes the request path a second time, leading to bypass of middleware on static paths (affects hono 4.13.1, pinned in package-lock.json).
- Medium Hono: Query parser reads parameters after the URL fragment, causing cache-key and proxy interpretation differentials (affects hono 4.13.1, pinned in package-lock.json).
- Medium Hono: Unbounded dot-notation nesting in `parseBody()` can cause memory exhaustion (affects hono 4.13.1, pinned in package-lock.json).
- Medium Hono: Incomplete fix for CVE-2026-39408: `toSSG()` still writes files outside the output directory (affects hono 4.13.1, pinned in package-lock.json).
- Medium hono/jsx renders plain strings unescaped in boundary components, leading to XSS (affects hono 4.13.1, pinned in package-lock.json).
- Medium ip-address: no classifier recognizes the NAT64 local-use range 64:ff9b:1::/48, allowing SSRF and trust-boundary bypass (affects ip-address 10.5.0, pinned in package-lock.json).
- Medium ip-address: Address6 builds a parse diagnostic proportional to the input with no length bound, allowing a single long string to stall or crash the process (affects ip-address 10.5.0, pinned in package-lock.json).
- Medium ip-address: isInSubnet() and isHostInSubnet() compare addresses of different families as if they shared an address space, allowing an allowlist check to admit an address outside its range (affects ip-address 10.5.0, pinned in package-lock.json).
- Medium ip-address: Address6.isLinkLocal() recognizes fe80::/64 rather than fe80::/10, allowing SSRF and trust-boundary bypass to on-link hosts (affects ip-address 10.5.0, pinned in package-lock.json).
- Medium ip-address: Address6 matches a zone identifier in quadratic time ahead of its length limit, allowing a single long string to stall the process (affects ip-address 10.5.0, pinned in package-lock.json).
- Medium undici vulnerable to cross-user cookie disclosure via Set-Cookie caching in shared caches (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Denial of Service via unhandled error in WebSocket permessage-deflate decompression (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Denial of Service via unbounded decompression of compressed responses (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Denial of Service via unbounded memory in the EventSource parser (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Subresource Integrity bypass via non-lowercase algorithm tokens (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Denial of Service via orphaned RetryHandler response body (affects undici 7.29.0, pinned in package-lock.json).
- Medium undici vulnerable to Denial of Service via WebSocketStream unclean close (affects undici 7.29.0, pinned in package-lock.json).
- Medium launch-editor: escapeCmdArgs() omits % escaping on Windows (affects vite 8.2.1, pinned in package-lock.json).
- Medium launch-editor: Editor CLI flag misinterpretation causing arbitrary command execution for some editors (affects vite 8.2.1, pinned in package-lock.json).
- Medium Vite: Files outside `server.fs.allow` could be served when project paths match system paths on non-Windows machine (affects vite 8.2.1, pinned in package-lock.json).
- Medium Vite: First 4 bytes of files outside of `server.fs` setting is exposed by `?vite-wasm-instance` (affects vite 8.2.1, pinned in package-lock.json).
- Medium Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock (affects vitest 4.1.10, pinned in package-lock.json).
- Low fast-uri vulnerable to scheme injection via an unescaped first-segment colon in suffix references (affects fast-uri 3.1.7, pinned in package-lock.json).
- Low fast-uri vulnerable to improper path equivalence in relative reference normalization (affects fast-uri 3.1.7, pinned in package-lock.json).
- Low undici vulnerable to response truncation via oversized chunked responses in the dump interceptor (affects undici 7.29.0, pinned in package-lock.json).
- Low undici vulnerable to caching and replay of unsafe HTTP method responses (affects undici 7.29.0, pinned in package-lock.json).
- Low undici vulnerable to downstream response splitting via retry interceptor (affects undici 7.29.0, pinned in package-lock.json).
- Low Vite: Cross origin script execution through Vite custom middleware (affects vite 8.2.1, pinned in package-lock.json).
- Low Downloads code and runs it straight away (a well-known installer), host raw.githubusercontent.com: scripts/install.sh, line 5.
- Note 219 files were not read (over 512 KB, or past the 60 file cap): src/node-request-preflight.ts, src/node-run-artifact-codecs.ts, src/node-run-artifact-presentation.ts and more.
- Note 3 of 399 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Alternatives
Alternatives to librarium
| Record | Type | How we know | Checked |
|---|---|---|---|
| Deep Research SkillThis is an alternative to it | Skill | Matched from the listing text | |
| ulw-researchThis is an alternative to it | Skill | Matched from the listing text |
Compare
Compare librarium side by side
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Security finding
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Deep Research Skill
Community
Community-maintained deep-research skill for Claude. Plan, search, synthesize, cite. The discovery loop, packaged.
ulw-research
code-yeongyu
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.