Context LatticeBLOCK
The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Open an agent. Already there.
The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
Quickstart · How it works · Agent setup · Architecture · Docs · Updates
Stop replaying the brief
Models can reason. Harnesses can act. Neither reliably retains the mission when a chat, model, tool, account, or computer changes.
ContextLattice gives that work a durable, inspectable context layer. It reconstructs the active objective, selects the evidence that matters, carries it safely, and records what actually worked—without turning every prompt into a transcript dump or making cloud storage mandatory.
425f4c29e86bOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add contextlattice-dashboard --env APPLE_CLIENT_SECRET=${APPLE_CLIENT_SECRET} --env APPLE_OAUTH_ENABLED=${APPLE_OAUTH_ENABLED} --env AUTH_RATE_LIMIT_MAX_ATTEMPTS=${AUTH_RATE_LIMIT_MAX_ATTEMPTS} --env AUTH_RATE_LIMIT_WINDOW_SECONDS=${AUTH_RATE_LIMIT_WINDOW_SECONDS} -- npx -y [email protected]{
"mcpServers": {
"contextlattice-dashboard": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"APPLE_CLIENT_SECRET": "${APPLE_CLIENT_SECRET}",
"APPLE_OAUTH_ENABLED": "${APPLE_OAUTH_ENABLED}",
"AUTH_RATE_LIMIT_MAX_ATTEMPTS": "${AUTH_RATE_LIMIT_MAX_ATTEMPTS}",
"AUTH_RATE_LIMIT_WINDOW_SECONDS": "${AUTH_RATE_LIMIT_WINDOW_SECONDS}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
qdrant-find-adv | read | # Embed the query |
Trust audit
BLOCKgrade F · trust 54/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (7 observation(s))
- Network
- declared (22 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
compaction-handoff-payload
--insecure-local Opt out of secure production defaults for local-only experimentation
--insecure-local)
ORCH_PGVECTOR_DSN=postgresql://postgres:postgres@pgvector-db:5432/contextlattice?sslmode=disable
ORCH_PGVECTOR_DSN=postgresql://postgres:postgres@pgvector-db:5432/contextlattice?sslmode=disable
"auto_escalate", "deep_async", "callback_url", "traffic_class",
"callback_url": "", "traffic_class": "evaluation_holdout", "graph_incremental_control": true,
"deep_async": false, "callback_url": "", "traffic_class": "evaluation_holdout",
"callback_url": "",
"callback_url": "", "traffic_class": firstNonEmptyStrings(trafficClass, "synthetic"),
CONTEXTLATTICE_ORCHESTRATOR_URL=http://127.0.0.1:8075
MEMMCP_ORCHESTRATOR_URL=http://127.0.0.1:8075
TASK_INFERENCE_CONTROL_PLANE_URL=http://127.0.0.1:8075
ORCH_ANE_SIDECAR_URL=http://127.0.0.1:9099
SGLANG_BASE_URL=http://127.0.0.1:30000
IyEvdXNyL2Jpbi9lbnYgYmFzaApzZXQgLWV1byBwaXBlZmFpbGUKClFfSE9TVD0iJHtRRFJBTlRfSE9TVDptaHR0cDovLzEyNy4wLjAuMX0iClFfUE9SVD0iJHtRRFJBTlRfUE9SVDo2MzMzfSIKQkFTRT0iJFFfSE9TVDokUFFfUE9SVCIKQ09MTD0iJHtRRFJBTlRf
token = "bench/results/fastembed_gate_latest.json"
token = "contextlattice_notes"
.nojekyll
> ln -svf "../../$(ENV_FILE)" infra/compose/.env >/dev/null
"../../config/agent_contracts/agent_output_contracts.json",
@next-auth/prisma-adapter, @prisma/client, bcryptjs, nodemailer, @types/bcryptjs, @types/node, @types/nodemailer, playwright
fastembed
v3.9.0 turns the Context Pack Quality Ledger from a passive endpoint into an agent-operable outcome loop. Agents can now carry the latest context-pack quality sample through their session and post com
docs/public_overview/assets/contextlattice-architecture-web-v2-2026-04-28.png
Gates applied: no_behavioural_pass.
425f4c29e86bfull audit observations/trust-audit/mcp-server/sheawinkler__context-lattice.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 425f4c29e86b | BLOCK | F | 54 | first audit |
Questions
What is the Context Lattice MCP server?
The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
What tools does Context Lattice expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Context Lattice safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (54/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Context Lattice need?
It reads APPLE_CLIENT_SECRET, APPLE_OAUTH_ENABLED, AUTH_RATE_LIMIT_MAX_ATTEMPTS, AUTH_RATE_LIMIT_WINDOW_SECONDS, AUTH_REQUIRED, AUTH_REQUIRE_EMAIL_VERIFICATION, CONTEXTLATTICE_ORCHESTRATOR_API_KEY, CONTEXTLATTICE_WORKER_API_KEY, GATE_REFRESH_API_KEY, GITHUB_SECRET, GOOGLE_CLIENT_SECRET and MEMMCP_ORCHESTRATOR_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Context Lattice run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as contextlattice-dashboard at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (425f4c29e86b), read on 2026-10-07. The repository is watched and re-audited when it changes.