150,000+ agents registered. Trust scores show their math.Explore →
Explorer/MCP/ampres-ai/talamus
✓ REGISTRY VERIFIEDLOCAL

Talamus

ampres-ai/talamus

Local-first, source-grounded memory with bitemporal history and provenance for AI agents.

16 tools available
The Ghost
This server runs locally on your machine. We can't scan it remotely; review the source code before installing.
Time indexed (1mo)
16toolsLocal/ STDIO1moindexed
Checked Aug 2, 2026
Quality Score
20/95
Emerging
Risk Score
0/100
Clean
How is this calculated?
Quality Breakdown
Tenure9.1/20
27 days indexed
Capability11.3/25
Tools: 6.3/13 (16 tools)
Description: 5/5
Endpoint: 0/7
Adoption0/25
Use count: 0/20 (0 uses)
Multi-registry: 0/5 (1 registry)
Reliability0/25
Currently live: 0/10
Uptime history: 0/15 No checks yet
Security scan: 0 pts in v1.0; ready to weight when coverage improves
Incomplete Data Cap (60)
Usage data is not available for this server. Quality is capped until adoption can be measured.
Risk
0Clean
No signals detected.
The scanner shows
This server runs locally. We can't scan it remotely; review the source code before installing.
First indexed Jul 20, 2026
Server Profile
Tools catalogued
16
16 tools available. Full list below.
Hosting
Local / STDIO
Runs on your machine. Has access to your filesystem, SSH keys, and environment variables.
Registry presence
Verified
Listed on the Official MCP Registry under Linux Foundation governance.
Liveness
No liveness checks recorded yet.
Publisher Verification
✓ Listed on the Official MCP Registry under Linux Foundation governance.
Tools (16)
search
Search the Talamus brain for notes relevant to a query; returns titles and summaries. With smart=True the query is expanded by the LLM before searching (Query2doc, cached): it breaks the lexical ceiling on vague questions, at the cost of one LLM call per new query.
read_note
Read the full Markdown content of a Talamus note given its title. Optional as_of (a date like "2026-01" or "2026-01-15"): read the note AS IT WAS at that moment — Talamus keeps every note's history, so you can check what was believed at a past date before trusting or updating it.
ask
Ask the brain and get a written answer WITH CITATIONS to the exact notes used. Spends LLM calls on the user's configured engine (cheap tier for the routing, strong tier for the answer). Prefer `recall` when you only need raw context to reason over yourself — it costs zero LLM calls.
verify
Check whether a note is still faithful to its ORIGINAL source (Talamus preserves the source of every note). Returns ok, a proposed correction, or unchecked when the source is unavailable. Costs one LLM call when the source exists — use it before relying on a note that smells stale.
recall
Recall from the Talamus brain the context relevant to a question (real notes). Reason over the context yourself to answer.
overview
Show the Talamus brain's domain map (name, description, note count): an overview to get oriented before searching. Read-only, no LLM cost.
Show all 16 tools ↓
neighbors
Show concepts connected to a concept in the brain, with relation types. include_inferred=False hides derived ontology-inference edges.
history
The past versions of a brain note (transaction time), oldest first: when Talamus changed that record and how.
sources
The sources (provenance) of a note: where each statement comes from.
ontology_status
The state of the emergent type system: schema version, active/candidate types, and the coverage of typed edges.
remember
Save into the Talamus brain an important insight or decision that emerged in the session, turning it into a note. scope: 'project' (default) or 'central' for the personal brain — writing to the global brain must be explicit.
ingest_text
Compile a text into brain notes (without the 'worth remembering' gate: use it for already-selected content). scope: 'project' (default) or 'central'.
propose_note
Propose UNCERTAIN knowledge: it lands in the brain's review queue, not directly in the notes (F10.4). A human will apply or reject it.
review_list
The decisions pending in the brain's review queue.
review_apply
Apply an item from the review queue (corrections are written to the brain while preserving history).
review_reject
Reject an item from the review queue (the decision stays recorded).

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
Similar servers
GCP MCP
Enables managing Google Cloud Platform resources through natural language commands in Claude Desktop, supporting comprehensive operations across compute, storage, databases, networking, monitoring, and IAM without manual credential setup.
MCP Embedding Search
A Model Context Protocol server that searches transcript segments in a Turso database using vector similarity, allowing users to find relevant content by asking questions without generating new embeddings.
ZoomEye MCP Server
MCP server for querying the ZoomEye API
adx-mcp-server
AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
Notion MCP Server
A Model Context Protocol server that connects Claude and other AI assistants to your Notion workspace, allowing AIs to interact with databases, pages, and blocks.
GZOO Cortex
Local-first knowledge graph for developers. Watches project files, extracts entities and relationships via LLMs, and lets you query across projects in natural language with source citations. Provides 4 MCP tools: get_status, list_projects, find_entity, query_cortex.
Indexed from Smithery · Confirmed on Official MCP Registry · Updates nightlyView on Smithery →