Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Libscope is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
7
downloads a day
local
runs on your machine
418
downloads in 30d
What it does
AI-powered knowledge base with MCP integration — query library docs, internal wikis, and topics with semantic search
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user libscope-mcp '--' npx -y libscope
# 2 — ask your agent for something these tools do
# search-docs, get-related, get-document and 31 more
Libscope costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ROAll 1 server
robertld1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Libscope as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user libscope-mcp '--' npx -y libscopeReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
34 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Semantic search across all indexed documentation, library docs, and topics
No parameter schema on file.
Find chunks semantically similar to a given chunk (more-like-this). Returns related content seeded from an existing chunk
No parameter schema on file.
Retrieve a specific document by its ID
No parameter schema on file.
Delete a document from the knowledge base by its ID
No parameter schema on file.
Update an existing document
No parameter schema on file.
Rate a document or suggest corrections. Use this when documentation appears outdated, incorrect, or particularly helpful.
No parameter schema on file.
Submit a new document for indexing into the knowledge base. You can provide content directly, or provide a URL to fetch and index automatically. Set spider=true to crawl linked pages from the URL.
No parameter schema on file.
List available documentation topics
No parameter schema on file.
Check the health of the LibScope server, including database connectivity, document and chunk counts, and FTS5 index status
No parameter schema on file.
List all indexed documents with optional filters
No parameter schema on file.
Ask a question and get an LLM-synthesized answer based on indexed documentation (RAG)
No parameter schema on file.
Re-embed all document chunks with the current embedding model. Use after switching embedding providers to update vectors without re-fetching content.
No parameter schema on file.
Sync Slack channel messages and threads into the knowledge base
No parameter schema on file.
Install a knowledge pack from the registry or a local file path
No parameter schema on file.
List installed knowledge packs or available packs from the registry
No parameter schema on file.
Sync OneNote notebooks via Microsoft Graph API
No parameter schema on file.
Sync pages and databases from a connected Notion workspace into the knowledge base
No parameter schema on file.
Sync an Obsidian vault into the knowledge base. Parses wikilinks, frontmatter, embeds, and tags with incremental sync support.
No parameter schema on file.
Sync Confluence spaces and pages into the knowledge base
No parameter schema on file.
View search analytics dashboard and knowledge gap detection
No parameter schema on file.
Create a relationship between two documents (see_also, prerequisite, supersedes, related)
No parameter schema on file.
Get all cross-reference links for a document (both outgoing and incoming)
No parameter schema on file.
Remove a cross-reference link between documents
No parameter schema on file.
Save a search query with optional filters for later re-use
No parameter schema on file.
Suggest tags for a document based on content analysis
No parameter schema on file.
List all saved searches
No parameter schema on file.
Execute a saved search by name or ID and return results
No parameter schema on file.
Delete a saved search by name or ID
No parameter schema on file.
Register a webhook to receive notifications for document events
No parameter schema on file.
List all registered webhooks
No parameter schema on file.
Remove a registered webhook by ID
No parameter schema on file.
Get the current status, progress, and result of an async background task
No parameter schema on file.
Request cancellation of a pending or running async background task
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public; its licence metadata reads SEE LICENSE IN LICENSE rather than naming a licence
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Libscope or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 2.0.1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings4 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digeste2088365263fc6eb7a7fe0acd6818baecd2fd5d6762d910a4fa6f6c582b9b1dc
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (2 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| link-documents | no tags | |
| task | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digeste2088365263fc6eb
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.0.1. Pin a release below and the command asks for exactly that one.
2.0.1
9 Oct 2026
latestNo release note was published with this version.
2.0.0
9 Oct 2026
No release note was published with this version.
1.8.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Libscope can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.