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
Opennous 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
Nous — the Context Graph for AI Agents.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @opennous/mcp
# 2 — ask your agent something
> Nous — the Context Graph for AI Agents.
Opennous is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
OPAll 1 server
@opennous1 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 Opennous 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 opennous-mcp -- npx -y @opennous/mcpReconnect, 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
38 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.
Get engineered context for a specific task about a person or company. Pass their email (or
Takes no parameters.
Example callreturns →
Get the full account record for a person or company — the durable FACTS we
Takes no parameters.
Example callreturns →
Merge two duplicate records for the SAME person into one account. Use when the same human exists
Takes no parameters.
Example callreturns →
REVERSE a merge — split a wrongly-merged duplicate back out into its own account. Identify the
Takes no parameters.
Example callreturns →
intro email
Takes no parameters.
Example callreturns →
Record a buying signal on a person or company — a concrete, current reason to reach out,
Takes no parameters.
Example callreturns →
Retrieve and summarise activity across many people. Three powers:\n
Takes no parameters.
Example callreturns →
Score a lead against our live ICP model and intent axis, and write the judgment into the graph so
Takes no parameters.
Example callreturns →
What needs your attention across the workspace right now — upcoming meetings and calls in the
Takes no parameters.
Example callreturns →
Outbound campaign feedback loop: how each cold-email/LinkedIn campaign and sequence step is landing,
Takes no parameters.
Example callreturns →
How the pipeline actually converts: how many accounts sit at each stage right now, the stage-to-stage
Takes no parameters.
Example callreturns →
The whole ACCOUNT PORTFOLIO in one call — every in-touch account with its deal health + band,
Takes no parameters.
Example callreturns →
Your open action items and commitments, pulled from meeting notes and emails — what you owe
Takes no parameters.
Example callreturns →
Re-check a specific fact before you act on it — e.g. an email or a deal stage that looks stale
Takes no parameters.
Example callreturns →
Read a FOUNDATION — the user
Takes no parameters.
Example callreturns →
Push a foundation
Takes no parameters.
Example callreturns →
Read INSIGHTS — what Nous learned about US from call transcripts, the mirror of the foundations/foundations
Takes no parameters.
Example callreturns →
Save a note or document onto a person or company so it is kept on their record — a meeting
Takes no parameters.
Example callreturns →
Propose a markdown file into the member
Takes no parameters.
Example callreturns →
Semantically search the saved notes & documents (meeting briefs, transcripts, meeting notes)
Takes no parameters.
Example callreturns →
See the whole setup state of this workspace in one call, plus a ranked NEXT STEPS list (each step
Takes no parameters.
Example callreturns →
Onboard the workspace, or update its basic profile. Nous is set up by you, the agent, in
Takes no parameters.
Example callreturns →
Build (or rebuild) the user
Takes no parameters.
Example callreturns →
Build (or sharpen) the ICP scoring model from the user
Takes no parameters.
Example callreturns →
Sync the user
Takes no parameters.
Example callreturns →
Get the LEARNED ICP scoring model (which signals predict a win, their weight, lift, and the
Takes no parameters.
Example callreturns →
Connect a key-based integration for the user — an enrichment, CRM, or sequencer provider that
Takes no parameters.
Example callreturns →
(Nous Cloud only) Configure how Nous keeps a connected CRM in sync — the same settings as the CRM Sync page. The
Takes no parameters.
Example callreturns →
(Nous Cloud only) Pull the latest from a connected CRM (HubSpot/Pipedrive/Attio) RIGHT NOW, instead of waiting for
Takes no parameters.
Example callreturns →
Scrape the people who commented or reacted on YOUR OWN recent LinkedIn posts into the native
Takes no parameters.
Example callreturns →
SEND a LinkedIn direct message for real, right now, from the workspace
Takes no parameters.
Example callreturns →
DRAFT a follow-up email for the operator to review and SEND themselves — you draft, they send.
Takes no parameters.
Example callreturns →
RETRACT an observation you recorded by mistake, and heal the record. Pass the observation
Takes no parameters.
Example callreturns →
DELETE a note saved by mistake. Pass the note
Takes no parameters.
Example callreturns →
List saved notes newest-first (chronological), optionally scoped to one person/company with
Takes no parameters.
Example callreturns →
List the integrations connected to this workspace (Gmail, HubSpot, Apollo, Instantly, LinkedIn, …)
Takes no parameters.
Example callreturns →
Report who this API key acts AS and who else is on the workspace — the agent
Takes no parameters.
Example callreturns →
Get the routing preferences that make this agent treat Nous as the DEFAULT for GTM — so it
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. Opennous 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
ATrust score 96 / 100
Release 0.51.0 · 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 score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digesta0316dc19cc5c61afc9f75160c9899cd0467a8f6c3d9c84eceab4546be88df31
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (38 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_context | no tags | |
| get_account | no tags | |
| merge_contacts | no tags | |
| unmerge_contacts | no tags | |
| record | no tags | |
| record_signal | no tags | |
| query | no tags | |
| score | no tags | |
| attention | no tags | |
| campaign_performance | no tags | |
| pipeline_intelligence | no tags | |
| pipeline | no tags | |
| get_action_items | no tags | |
| verify | no tags | |
| get_foundation | no tags | |
| sync_foundation | no tags | |
| get_insights | no tags | |
| save_note | no tags | |
| propose_vault_file | no tags | |
| search_notes | no tags | |
| get_workspace_status | no tags | |
| set_workspace_profile | no tags | |
| build_icp_model | no tags | |
| train_icp_model | no tags | |
| sync_icp | no tags | |
| export_icp_model | no tags | |
| connect_integration | no tags | |
| configure_crm_sync | no tags | |
| sync_crm_now | no tags | |
| scrape_engagers | untrusted-input | |
| send_linkedin_message | no tags | |
| draft_email | no tags | |
| retract_observation | no tags | |
| delete_note | no tags | |
| list_notes | no tags | |
| list_integrations | no tags | |
| whoami | no tags | |
| get_routing_preferences | no tags |
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 digesta0316dc19cc5c61a
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 0.51.0 — 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.
0.51.0
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 Opennous 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.