MCP server for 0Latency — persistent memory layer for AI agents. Give Claude, Cursor, or any MCP client long-term memory.
Free
Nothing to run from here
Context Mem 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional LLM judge), entity intelligence, decision trails, Obsidian plugin. Fully local, zero cost. MIT.
Quickstart
# 1 — run it from where its publisher ships it
npx -y context-mem
# 2 — ask your agent something
> Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional
Context Mem is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
COAll 1 server
context-mem1 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 Context Mem 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add context-mem-mcp -- npx -y context-memReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
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
44 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.
Register the current session as a named agent for multi-agent coordination.
Takes no parameters.
Example callreturns →
List all active agents with their tasks and claimed files.
Takes no parameters.
Example callreturns →
Claim files for the current agent. Returns conflicts if already claimed by another agent.
Takes no parameters.
Example callreturns →
Broadcast a message to all active agents via the event system.
Takes no parameters.
Example callreturns →
Store a new observation (content snippet) into context memory with automatic summarization.
Takes no parameters.
Example callreturns →
Summarize a piece of content using the matching summarizer plugin without storing it.
Takes no parameters.
Example callreturns →
Retrieve observations in reverse-chronological order with optional filters.
Takes no parameters.
Example callreturns →
Retrieve a single observation by its ID.
Takes no parameters.
Example callreturns →
Get token economy statistics for the current session.
Takes no parameters.
Example callreturns →
Update a mutable configuration key at runtime.
Takes no parameters.
Example callreturns →
Query the knowledge graph. Find entities and their relationships.
Takes no parameters.
Example callreturns →
Add a relationship between two entities in the knowledge graph. Creates entities if they do not exist.
Takes no parameters.
Example callreturns →
Find all entities connected to a given entity. Faster than graph_query for simple lookups.
Takes no parameters.
Example callreturns →
Extract entities (technologies, people, files, components) from text content.
Takes no parameters.
Example callreturns →
List all detected person entities with relationship counts.
Takes no parameters.
Example callreturns →
Save a knowledge entry with automatic contradiction detection. When contradictions are found, the save is blocked — resubmit with force: true to save anyway.
Takes no parameters.
Example callreturns →
Promote a project knowledge entry to the global cross-project knowledge store. Privacy engine sanitizes content before storing.
Takes no parameters.
Example callreturns →
Search the global cross-project knowledge store.
Takes no parameters.
Example callreturns →
View pending merge suggestions for duplicate global knowledge entries.
Takes no parameters.
Example callreturns →
Resolve a contradiction between knowledge entries by merging, superseding, or keeping both.
Takes no parameters.
Example callreturns →
Query knowledge that was valid at a specific point in time. Returns facts that were active at the given timestamp.
Takes no parameters.
Example callreturns →
Generate a human-readable narrative from session data. Formats: pr (pull request), standup, adr (architecture decision record), onboarding.
Takes no parameters.
Example callreturns →
Reconstruct the evidence chain behind a code change or decision. Returns the trail of events that led to a decision.
Takes no parameters.
Example callreturns →
Predict which memory entries are at highest risk of being forgotten or archived. Users can pin important entries to protect them.
Takes no parameters.
Example callreturns →
Generate a scored session primer with 4-layer context: project profile, critical knowledge, recent decisions, and top entities.
Takes no parameters.
Example callreturns →
[v4] Unified search across observations, knowledge, content, topics. Legacy search/search_knowledge/search_content/recall/browse/global_search/ask are aliased to this with deprecation _meta.
Takes no parameters.
Example callreturns →
Index content into the content store with code-aware chunking for later search.
Takes no parameters.
Example callreturns →
Search the content store for indexed content chunks.
Takes no parameters.
Example callreturns →
Search the knowledge base using 3-layer search (FTS5 → trigram → scan). Optionally include global cross-project knowledge. By default only returns currently-valid facts (valid_to IS NULL).
Takes no parameters.
Example callreturns →
Verbatim memory retrieval with importance filtering and rich attribution. Returns original content, not summaries.
Takes no parameters.
Example callreturns →
Ask a natural language question about the project. Searches knowledge, observations, events, and graph entities.
Takes no parameters.
Example callreturns →
Browse observations by topic, person, or time dimension.
Takes no parameters.
Example callreturns →
Update the project quick profile — a 3-5 line summary shown at every session start. Auto-generates from knowledge if no content provided.
Takes no parameters.
Example callreturns →
Get current budget usage and status for the session.
Takes no parameters.
Example callreturns →
Configure budget settings (session limit, overflow strategy).
Takes no parameters.
Example callreturns →
Restore a previous session snapshot by session ID.
Takes no parameters.
Example callreturns →
Emit a context event with priority and metadata.
Takes no parameters.
Example callreturns →
Query context events with optional filters.
Takes no parameters.
Example callreturns →
View or compare the project state at any point in time. Shows observations, knowledge, and events as of a target date.
Takes no parameters.
Example callreturns →
Import external conversation exports (Claude, ChatGPT, Slack, plaintext) into context memory.
Takes no parameters.
Example callreturns →
List all detected topics with observation counts.
Takes no parameters.
Example callreturns →
Find topics that appear in 2+ projects (cross-project knowledge bridges).
Takes no parameters.
Example callreturns →
Query internal error log. Shows what context-mem subsystems have failed at (embedder, entity extraction, topic storage, dreamer, etc.). Useful for doctor-style debugging.
Takes no parameters.
Example callreturns →
Generate session handoff — saves state and returns continuation prompt for a new session. Use when context is running low or before ending a session.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Context Mem costs nothing to install and nothing to call, 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: $8.42
$16.58 left
BTrust score 83 / 100
Release 4.0.0 · scanned 25 Aug 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 score91
Client score83
Findings4 threat · 14 capability
Capabilityhigh
Coveragesource
Verificationnone
Surface digest4a3d61e53db2198bc21106564f1f89694d6cbda75d63f22ce01b27cc0be384cc
Score vectorthreat 91 → client 83
| Term | Level | What it prices | Points |
|---|---|---|---|
| −6.3 | |||
| −3.15 | |||
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can send data / act on an external service
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 digest4a3d61e53db2198b
Scanned2026-08-25
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
Pinned to 4.0.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
4.0.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Context Mem in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.