Reported issues for Local FAISS MCP Server
Pod holds 11 of 11 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to Local FAISS MCP Server.
Most discussed
Extract and store document metadata (author, date, tags)
Extract rich metadata from documents for better search and organization.
Why: Metadata enables filtering by date, author, document type, etc.
Expected behavior:
$ local-faiss list --metadata
Documents:
1. research_paper.pdf
Author: John Doe
Created: 2024-01-15
Pages: 42
Tags: machine-learning, RAG
Chunks: 15
$ local-faiss search "neural networks" --filter "created:2024"
Implementation approach:
- Extract PDF metadata using pypdf (author, title, creati
Read the thread · 2025-12-09 · closed · 4 comments
What’s the right memory abstraction for MCP-based agents?
I built this MCP server to explore local-first memory using FAISS.
What I’m running into is that the interaction model feels fundamentally wrong.
Having to tell an agent “use the vector DB” or “store this in FAISS” is not how memory should work. Memory should be implicit, contextual, and constrained — not a tool the user has to invoke.
This makes me question:
when an agent should decide to persist something at all? whether memory should be event-driven vs query-driven? how to avoid polluting
Read the thread · 2025-12-20 · closed · 2 comments
[Feature] Bring your own embedding model
User wants to specify any local embedding model. This feature can be triggered ad deployment time:
local-faiss-mcp --embed [model]
The --embed flag will take in Huggingface model names and defaults to the current embedding model: 'all-MiniLM-L6-v2'
Read the thread · 2025-12-02 · closed · 2 comments
[Feature] Query highlight
User wants to retrieve the most relevant section within the document to answer the query. This can be done through a pipeline or providing a MCP prompt to the model. See https://modelcontextprotocol.io/specification/2025-06-18/server/prompts for more information about MCP prompts.
An MCP prompt for answer extraction and quotation can have as inputs the original query and each of the retrieved / top k documents.
Read the thread · 2025-12-02 · closed · 2 comments
[Feature] Support re-ranking models
User can trigger re-ranking models in the search pipeline with flag at deployment time:
local-faiss-mcp -rerank [model]
The rerank flag takes in a Huggingface model name or defaults to a known reranking model, such as Qwen/Qwen3-Reranker-0.6B.
Read the thread · 2025-12-02 · closed · 2 comments
[Feature] CLI to index documents outside model context
The user will be able to index a file, usually of document type (pdf, docx, txt, md), by issuing a bash command of the form:
local-faiss index [-i index_path] [-f/--folder folder_path] document1 document2 document3
The user can also search using local-faiss:
local-faiss search [-i index_path] "natural language text query from user"
Read the thread · 2025-12-02 · closed · 1 comment
Add delete and update commands for index management
Users need to remove or update documents in the index without rebuilding everything.
Why: Currently, there's no way to remove indexed documents except deleting the entire index.
Expected behavior:
# Delete a document
$ local-faiss delete document.pdf
Removed 15 chunks from index
# Update a document (delete + re-index)
$ local-faiss update document.pdf
Updated 12 chunks (was 15)
# List what would be deleted
$ local-faiss delete --dry-run "docs/*.pdf"
Would delete:
- docs/file1
[Read the thread](https://github.com/nonatofabio/local_faiss_mcp/issues/10) · 2025-12-09 · open · 0 comments
### Add hybrid search combining BM25 and vector similarity
Implement hybrid search that combines lexical (BM25) and semantic (vector) search for better results.
**Why**: Hybrid search outperforms pure vector search by combining keyword matching with semantic similarity.
**Expected behavior**:
```bash
$ local-faiss search --hybrid "FAISS algorithm"
Or via MCP config:
{
"args": ["--index-dir", "./.vector_store", "--search-mode", "hybrid"]
}
Implementation approach:
- Add BM25 indexing during document ingestion (using
rank-bm25
Read the thread · 2025-12-09 · open · 0 comments
Most recent
Show progress bar when indexing multiple files
Add a progress bar using tqdm when indexing multiple documents.
Why: Users need feedback during long batch operations.
Expected behavior:
$ local-faiss index documents/*.pdf
Indexing 50 files...
██████████████░░░░░░ 15/50 (30%) - document_15.pdf
Implementation hints:
- Add
tqdm>=4.66.0to dependencies - Wrap file loop in
cli.py::cmd_index() - Show: current file, X/Y, percentage, filename
- Disable for single file (no progress bar needed)
Acceptance criteria
Read the thread · 2025-12-09 · closed · 0 comments
Add colored output to CLI for better readability
Enhance CLI with colors using colorama or rich for better user experience.
Why: Colored output makes success/error states instantly recognizable.
Expected behavior:
- ✅ Green: Success messages ("✓ Added 5 chunks")
- ❌ Red: Errors ("✗ File not found")
- 📘 Blue: Info messages ("Using MCP config: .mcp.json")
- ⚠️ Yellow: Warnings ("Warning: Large file may take time")
Implementation hints:
- Add
colorama>=0.4.6to dependencies - Create color helper functions in
cli.py - Update
Read the thread · 2025-12-09 · closed · 0 comments
Add local-faiss list command to show indexed documents
Add a new CLI command to list all documents in the index with their metadata.
Why: Users need visibility into what's indexed without querying.
Expected behavior:
$ local-faiss list
Indexed Documents (3 total):
1. research_paper.pdf
- Chunks: 15
- Indexed: 2024-12-08 14:23
2. readme.md
- Chunks: 3
- Indexed: 2024-12-08 14:25
3. notes.txt
- Chunks: 8
- Indexed: 2024-12-08 15:10
Implementation hints:
- Add
cmd_list()function incli.py - Read from
Read the thread · 2025-12-09 · closed · 0 comments
The remaining reports are on the project's issue tracker.