A read-only MCP server for searching and browsing a local AI knowledge base powered by hybrid vector + full-text retrieval. It exposes four tools:
search(query, limit, hybrid) — Perform semantic or hybrid (vector + FTS → RRF fusion → optional cross-encoder rerank) searches. Supports configurable result limits and hybrid mode toggle. Results cite source_id/source_url, never raw filepaths.
discover(mode, days, limit) — Browse content without a specific query using four non-ranking modes:
digest — Recent items over a configurable time window (default: last 7 days)
random — Random content exploration
concepts — Top mentioned terms via heuristic extraction
channels — Content grouped by source channel
get_context(query, include_recent) — Retrieve comprehensive context for a query, optionally appending a recent digest for broader situational awareness.
get_status() — Check knowledge base statistics (document counts, tracked channels) and Ollama/embedding service health.
Note: Mutation tools (
add_channel,sync_now) are not available on the public profile — this server is strictly read-only unless the private env flagAI_KB_MCP_PRIVATE=1is set locally.
Allows ingestion of YouTube video transcripts from configured channels, enabling semantic and hybrid search over their content.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AI Knowledge Base MCP Server search for 'hybrid retrieval' concepts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Keep coding agents current with local hybrid RAG + MCP.
Public demo uses synthetic fixtures; the architecture is the product.
AI techniques move weekly. Coding agents that only “know” last quarter’s defaults fall behind. Teams need a local, citable knowledge path — retrieve what matters, cite sources, and expose tools agents can call — without shipping a private corpus to the public internet.
flowchart LR
F[Fixtures / sources] --> I[Ingest + embed]
I --> D[(LanceDB)]
Q[Query] --> S[Hybrid search]
D --> S
S --> M[CLI / MCP tools]
M --> A[Coding agents]Ingest documents (committed fixtures for the public demo).
Embed locally (Ollama nomic-embed-text).
Retrieve with vector + keyword fusion, optional cross-encoder.
Serve results via CLI and read-only MCP tools (search, discover, get_context, get_status).
Hybrid fusion before cross-encoder — the retrieval spine stays useful if the reranker degrades or is disabled.
Public fixtures / private corpus split — strangers get a working demo; personal tip libraries stay off this repo.
MCP read-only by default — mutations stay behind an explicit private profile flag.
uv sync
ollama pull nomic-embed-text
uv run python -m src.ingest --fixtures
uv run python -m src.search "reciprocal rank fusion RRF" --hybrid --db data/lancedb
uv run python -m src.evalMCP wiring, discovery commands, and optional BYO YouTube overlay: GETTING_STARTED.md.
Component | Tool |
Vector + FTS | LanceDB |
Embeddings | Ollama · |
Rerank (optional) | MiniLM cross-encoder (degrades to fusion) |
Agent surface | MCP (public profile = read-only) |
docs/PORTFOLIO_VISION.md — packaging intent
docs/ARCHITECTURE.md — contracts / how
GETTING_STARTED.md — operator path
FAQ.md — Technical FAQ
docs/2026-07-12_ce_keep_note.md — cross-encoder keep note
LICENSE — PolyForm Noncommercial 1.0.0 (source-available / non-commercial)
Building agent knowledge systems? Reach me on LinkedIn.
Discover AI content without a specific query (honest browse/digest/heuristics).
Modes: random, digest, concepts, channels — not a ranking product.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| mode | No | digest | |
| limit | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only hints at behavior with 'honest browse/digest/heuristics' without explaining modes, limitations, or auth needs. Lacks detail on how the tool works.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very short and minimal, but contains key purpose and mode list. Could be better organized, and brevity sacrifices parameter description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite output schema existing, description omits what the tool returns or how the modes behave. With 3 parameters and no annotations, more context is needed for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and description only lists mode options without explaining their meanings, nor does it describe days or limit parameters. Minimal information beyond schema defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool discovers AI content without a specific query, lists modes, and contrasts with ranking products. This effectively distinguishes it from siblings like search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage when no specific query is needed, but does not explicitly state when not to use it or name alternatives. The sibling search would be for queries, but no direct contrast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get comprehensive context via shared retrieval (+ optional recent digest).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| include_recent | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It mentions 'comprehensive context' and 'optional recent digest' but does not describe side effects, performance implications, or what happens on missing data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the primary action, no wasted words. It is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With two parameters and no annotations, the description lacks depth. It does not explain output, error conditions, or how this tool differs from siblings like search. The agent needs more context to decide when to use it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explicitly describe the parameters. The mention of 'recent digest' hints at include_recent, but query is not explained. The description adds minimal value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves context via shared retrieval with an optional recent digest. It distinguishes from siblings like search and discover by specifying 'context' and 'shared retrieval', though the exact meaning of 'shared retrieval' is vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like search or discover. It does not mention prerequisites or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current status of the AI knowledge base.
Does not require embedding / Ollama for index stats (Ollama health is reported).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description discloses that it does not require embedding/Ollama for index stats and reports Ollama health, which are important behavioral traits beyond a simple status check.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, and includes necessary nuance about dependencies. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with an output schema, the description adequately explains what the tool returns and the key nuance about Ollama. It is complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so the schema provides all needed info. The description adds no parameter details, but with 0 parameters, the baseline is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'current status of the AI knowledge base', and distinguishes itself from siblings by noting the Ollama dependency details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking status but does not explicitly state when to use or when alternatives like search or discover are better. The sibling tools are different, but no direct guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the AI knowledge base for relevant content.
Uses the shared retrieval spine (hybrid → fusion → optional CE). Public results cite source_id / source_url — never absolute filepath.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| hybrid | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It explains that results cite source_id/source_url (not absolute filepath) and outlines the retrieval pipeline. However, it does not disclose if the tool is read-only, destructive, or any authorization requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three succinct sentences with no wasted words. Front-loaded with the primary purpose, then adds behavioral context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description credits the return format. It covers core behavior and a notable constraint (no absolute filepath). Missing details like pagination, ranking, or error handling, but adequate for a straightforward search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any of the three parameters (limit, query, hybrid). With 0% schema description coverage, the description fails to add meaning beyond what the schema's type, title, and default provide. For example, it could explain hybrid search behavior but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches an AI knowledge base and mentions the retrieval spine (hybrid → fusion → CE), but does not strongly differentiate from sibling tools like 'discover' or 'get_context'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. It mentions the shared retrieval spine but does not indicate when to prefer search over discover or get_context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0discoverget_contextget_statussearchEach tool has a distinct purpose: discover for exploration, search for query-based retrieval, get_context for comprehensive context, and get_status for system health. However, get_context and search may cause slight confusion as both involve retrieval.
Tool names are verbs but mix single-word (discover, search) and verb_noun patterns (get_context, get_status). This inconsistency could be improved by normalizing to a single pattern.
Four tools is a minimal but reasonable set for a knowledge base query interface. It covers core functions without bloat, though it could be expanded slightly for more granularity.
The toolset focuses on reading and exploration but lacks write operations (e.g., add, update, delete content). This may hinder agents needing to modify the knowledge base.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search your knowledge bases from any AI assistant using hybrid RAG.
Self-hosted AI-native knowledge workspace with hybrid search, GraphRAG, and MCP.
Search ATProto writing, annotations, identity, agents, and forum posts. 12 read-only tools.
Read-only search of your Sortio knowledge graph (files and entities) for Claude and ChatGPT.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Alpha-W0lf/ai-knowledge-base-public'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
