Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Vibe Hnindex 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.
94/100
trust score
13
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Index source code into a local knowledge base, search with keyword + semantic + hybrid modes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user vibe-hnindex-mcp '--' npx -y vibe-hnindex
# 2 — ask your agent for something these tools do
# index_codebase, index_file, search and 30 more
Vibe Hnindex costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ANAll 1 server
AndyAnh1741 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 Vibe Hnindex 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 vibe-hnindex-mcp '--' npx -y vibe-hnindexReconnect, 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 asks of you
Nothing is required, but it can take OLLAMA_URL (Ollama embedding server URL), OLLAMA_MODEL (Ollama embedding model name (default: bge-m3:567m)), QDRANT_URL (Qdrant vector database URL), STORAGE_PATH (SQLite database storage path) if you want to set them.
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
33 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.
Index an entire codebase directory for later search. Scans all supported source files, chunks them, and stores in the knowledge base with keyword and semantic indexes. Supports incremental indexing — unchanged files are skipped.
No parameter schema on file.
Index or re-index a single file in an existing project. The project must have been indexed with index_codebase first.
No parameter schema on file.
No parameter schema on file.
List all indexed projects with their metadata including file count, chunk count, and last indexed time.
No parameter schema on file.
Health check: Ollama, Qdrant, embedding probe, and config summary. Optionally pass project_name to compare SQLite chunk count with Qdrant point count.
No parameter schema on file.
Short markdown stub for CLAUDE.md / AGENTS.md: project path, index stats, optional package.json script hints (test/build/lint), rule-based bullets — not a full project_briefing.
No parameter schema on file.
Delete a project and all its indexed data from the knowledge base (both SQLite and Qdrant).
No parameter schema on file.
Get information about a specific indexed file including its chunks, line ranges, and language.
No parameter schema on file.
Get detailed statistics about an indexed project: language breakdown, file/chunk counts, total lines, and averages. Useful for understanding codebase composition before searching.
No parameter schema on file.
Start watching an indexed project for file changes. When a source file is saved, it will be automatically re-indexed. Uses debouncing to avoid excessive re-indexing.
No parameter schema on file.
Stop watching a project for file changes.
No parameter schema on file.
Get a high-level overview of an indexed project: directory structure, language breakdown, entry points, detected frameworks, and key exports. Useful for understanding codebase architecture without reading every file.
No parameter schema on file.
Rule-based project briefing from README, CLAUDE.md, package.json, and indexed stats (no LLM). Results are cached in SQLite until the index fingerprint changes.
No parameter schema on file.
Single markdown blob for agent onboarding: cached project briefing, stats, and optional recent git activity. Output is truncated to max_chars.
No parameter schema on file.
Find symbol definitions (classes, functions, interfaces, methods) by name in the indexed symbol table. Faster than full-text search for exact identifiers. Re-index the project if results are empty.
No parameter schema on file.
Get a detailed summary of a specific file: purpose, exports, imports, files that depend on it, and complexity. More efficient than reading the full file.
No parameter schema on file.
List all imports/dependencies of a specific file. Shows what this file depends on.
No parameter schema on file.
List all files that import/depend on a specific file. Shows what would be affected if this file changes.
No parameter schema on file.
Analyze the transitive impact of changing a file. Uses BFS to find all direct and indirect dependents up to a configurable depth. Essential before refactoring.
No parameter schema on file.
Show recent git commits for a project with changed files cross-referenced against the index. Requires git.
No parameter schema on file.
Get comprehensive context for a file, task, or question. v0.10.0: now supports task-aware analysis (impact, test files, similar patterns) and question-based code search. Ideal before editing, debugging, or understanding code.
No parameter schema on file.
No parameter schema on file.
Apply code changes (create, modify, delete files) proposed by the AI. Respects CODE_AGENT_SCOPE for safety. Optionally runs test suite and linting after applying. Use after code_session to implement the planned changes.
No parameter schema on file.
Manage chat memory: save conversation messages, load previous context, ingest entire conversation threads, or clear old context. Auto-track is always on when CHAT_MEMORY_ENABLED=true — search, smart_context, and code_session calls are logged automatically without calling this tool.
No parameter schema on file.
Recent chat context and tool-auto tracked history for a project. Loaded by AI clients on session start to restore working context.
No parameter schema on file.
Dump MCP tool priority enforcement rules into the conversation. Call this when the AI agent is using grep/cat/Glob instead of MCP tools. Returns compact rules the AI must follow.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 published under MIT
- 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 Vibe Hnindex 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 94 / 100
Release 0.15.3 · scanned 15 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 score94
Findings3 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest27b529eb00d24095ba4074188c307385a536b6ac91e5e95a615faafd76032acd
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (33 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>".
4 of the 33 recovered tools are registered only when config.codeGraphEnabled holds (dist/index.js:111) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
2 of the 33 recovered tools are registered only when config.codeAgentEnabled holds (dist/index.js:255) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
1 of the 33 recovered tools are registered only when config.chatMemoryEnabled holds (dist/index.js:275) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
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. high is the level these add up to.
26 tools are registered unconditionally · (1) 4 more only when config.codeGraphEnabled holds (dist/index.js:111) · (2) 2 more only when config.codeAgentEnabled holds (dist/index.js:255) · (3) 1 more only when config.chatMemoryEnabled holds (dist/index.js:275) — typically when a key or option is configured. All 33 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| workspace_context | no tags | |
| locate_code | no tags | |
| index_codebase | no tags | |
| index_file | no tags | |
| index_code_graph conditional (1) | no tags | |
| find_references conditional (1) | no tags | |
| callers conditional (1) | no tags | |
| graph_context conditional (1) | no tags | |
| evaluate_retrieval | no tags | |
| search | no tags | |
| list_projects | no tags | |
| server_diagnostics | no tags | |
| agent_rules_stub | no tags | |
| delete_project | no tags | |
| get_file_info | no tags | |
| project_stats | no tags | |
| watch_project | no tags | |
| unwatch_project | no tags | |
| codebase_overview | no tags | |
| project_briefing | no tags | |
| onboarding_prompt | no tags | |
| symbol_lookup | no tags | |
| file_summary | no tags | |
| get_dependencies | no tags | |
| get_dependents | no tags | |
| impact_analysis | no tags | |
| recent_changes | no tags | |
| smart_context | no tags | |
| code_session conditional (2) | no tags | |
| code_apply conditional (2) | no tags | |
| chat_context conditional (3) | no tags | |
| benchmark_search | no tags | |
| priority_prompt | 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 digest27b529eb00d24095
Scanned2026-10-15
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 0.15.3. Pin a release below and the command asks for exactly that one.
0.15.3
6 Oct 2026
latestNo release note was published with this version.
0.14.0
1 Oct 2026
No release note was published with this version.
0.12.1
15 Jun 2026
No release note was published with this version.
0.1.2
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 Vibe Hnindex 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.