mcpintake

Local FAISS MCP Server

Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.

MCP declaredAPI not recordedCost unknownLicence unknown

Plan with Local FAISS MCP Server Open homepage

[ Observed sample ]

Frequency in Leyline's observed sample

The count is distinct observed stacks. It is not a Score input.

This component is not in Leyline's observed sample.

Record cmp_local-faiss-mcp-server

Open ranks

[ Score explain ]

Why the Score is 6

How Score works

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

10% weight × 0.33 value

3.3 points

An MCP surface is declared. No API is declared. Cost is unknown. 1 of 3 checklist fields are complete.

14% weight × 0.18 value

2.5 points

1 sources cover 1 evidence types. The latest dated evidence is 2026-10-16. Freshness is omitted unless observed as a signal.

insufficient evidence

insufficient evidence

insufficient evidence

Total5.87 → 6 after rounding

GitHub health: insufficient evidence

Agent use: insufficient evidence

Human notes: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind: mcp
Interfaces: Interface
mcp
Model Context Protocol server
Functions: Function
Connect
speak a protocol (MCP, API, CLI)
Connect Browse Connect

Function
Memory
keep context across turns
Memory Browse Memory

Function
Code
write or edit programs
Code Browse Code

Function
Embed
turn content into vectors
Embed Browse Embed

Function
Extract
pull a fact or field out
Extract Browse Extract

Function
Index
make retrieval cheap
Index Browse Index

Function
Ingest
bring raw material in
Ingest Browse Ingest

Function
Retrieve
fetch stored knowledge
Retrieve Browse Retrieve

Function
Search
find by query
Search Browse Search

Function
Store
persist state
Store Browse Store

Function
Rank
order candidates by trust or fit
Rank Browse Rank
Tags: None recorded
mcp: unverified · asserted true · https://github.com/nonatofabio/local_faiss_mcp
api: unverified · asserted false · https://github.com/nonatofabio/local_faiss_mcp
cost: unverified · asserted unknown · https://github.com/nonatofabio/local_faiss_mcp
license: unverified · asserted · https://github.com/nonatofabio/local_faiss_mcp

[ Capability slices ]

Compose the useful parts.

ingest

Document ingestion

ingest_document accepts text or a file path and chunks documents into the local store.

UnknownCompose with this

extract

Answer extraction prompt

MCP prompt extract-answer formats cited answers from retrieved chunks.

UnknownCompose with this

retrieve

RAG retrieval

query_rag_store returns relevant document chunks for a natural-language query.

UnknownCompose with this

index

CLI and server indexing

local-faiss index and the MCP server write FAISS indexes under a configurable index directory.

UnknownCompose with this

embed

Sentence embeddings

Configurable Hugging Face sentence-transformers embedding models; default all-MiniLM-L6-v2.

UnknownCompose with this

memory

Agent memory store

Positioned as local agent memory and drop-in semantic search for Claude, Copilot, and agents.

UnknownCompose with this

connect

Inferred from executor

UnknownCompose with this

code

Inferred from executor

UnknownCompose with this

Search

Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.

unknownCompose with this

store

Store

Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.

unknownCompose with this

rank

Rank

Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.

unknownCompose with this

Declared as a Model Context Protocol server with stdin/stdout MCP tool calls (ingest_document, query_rag_store) and MCP prompts (extract-answer, summarize-documents). It is described as usable with MCP-compatible agents and clients, plus a standalone local-faiss CLI that can reuse MCP config files. No non-MCP HTTP API is stated.

[ Relations ]

Derived alternatives and shared slots

Alternative to
memini Shared functions code, connect, embed, memory, rank, retrieve, search, store. Same kind and overlapping capability.
Fills the same slot as
Build software better, together Shared functions code, connect, index, ingest, memory, retrieve. Can fill the same function slot.
Fills the same slot as
Lore Shared functions connect, extract, memory, retrieve, search, store. Can fill the same function slot.
Fills the same slot as
Self Shared functions code, connect, embed, index, rank, search. Can fill the same function slot.
Fills the same slot as
cognee Shared functions code, connect, embed, memory, retrieve. Can fill the same function slot.
Fills the same slot as
awesome Shared functions code, connect, index, memory, search, store. Can fill the same function slot.
Fills the same slot as
LlamaIndex Shared functions embed, index, ingest, memory, retrieve. Can fill the same function slot.
Fills the same slot as
PulseMCP Shared functions connect, index, ingest, retrieve, search. Can fill the same function slot.

[ Signals ]

Observed evidence and source claims

Signals carry source, method, and observedAt. Source review dates and evidence basis are shown separately. Unobserved metrics stay insufficient evidence.

web
executor
Evidence basis unknown · Check date unknown · Source date 2026-10-16

No social source is stored.

Suggest a correction

Propose a change with a public source. Corrections wait for review before the card changes.

[ Notes ]

No notes are stored.