CTXBLOCK
CTX - Context Runtime Engine for Coding Agents
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
CTX
The context layer for AI coding agents
Reduce token waste in OpenCode and AI coding workflows with graph memory, compact task packs, read-cache compression, command pruning, and a live right-sidebar dashboard.
OpenCode-first runtime · Local MCP tools · Read cache + delta-aware indexing · Single Rust binary
Install · OpenCode Usage · Dashboard · Benchmarks · Docs · Security
CTX is a local context runtime for OpenCode and AI coding agents. It keeps repository knowledge, reusable rules, shell output, diffs, and file rereads compact before they ever bloat the model context.
See It In Action
Contents
- What CTX Is
- Why It Exists
- Install CTX
- OpenCode-First Usage
- [What Works Today](#what-works-to
711da03f8a33OBSERVED · 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.
claude mcp add ctx-bin -- npx -y @alegau/[email protected]
{
"mcpServers": {
"ctx-bin": {
"command": "npx",
"args": [
"-y",
"@alegau/[email protected]"
]
}
}
}Exposed tools (15)
11 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
get_compact_diff | read | Return query-focused compact diff |
get_relevant_context | read | Return compact context for current query |
memory_bootstrap_markdown | write | Auto-import conventional markdown rule files into graph memory |
memory_delete | destructive | Delete one graph memory directive |
memory_directives | read | Graph-backed operational directives replacing markdown habit files |
memory_get | read | Get one graph memory directive |
memory_import_markdown | write | Import AGENTS/CLAUDE/CODEX markdown rules into graph memory |
memory_list | read | List graph-backed memory directives |
memory_search | read | Search graph memory directives by topic |
memory_set | write | Create/update one graph memory directive |
project_map | read | Return top-level repository map |
read_path | read | Read one repository file using full, outline, or digest mode with reread cache awareness |
recent_decisions | read | Return recent pruning/decision notes |
related_failures | read | Return failures connected to symbols/tasks |
search_symbols | read | Search indexed symbols by keyword |
Trust audit
BLOCKgrade D · trust 69/100 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 | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (4 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (22)
"id_rsa".to_string(),
"url": format!("http://127.0.0.1:{port}/rpc"),"health": format!("http://127.0.0.1:{port}/health"),memory_delete
sensitive_patterns = [".env", "id_rsa", ".pem", ".key", "credentials", "secret"]
sensitive_patterns = [".env", "id_rsa", ".pem", ".key", "credentials", "secret"]
sensitive_patterns = [".env", "id_rsa", ".pem", ".key", "credentials", "secret"]
println!("cargo:rerun-if-changed=../../.git/HEAD");println!("cargo:rerun-if-changed=../../.git/index");let template = std::fs::read_to_string("../../templates/config.default.toml")import { handleRefreshRoute } from "../../src/http/refresh-route";import { refreshSession } from "../../src/auth/session";typescript, vitest
docs/assets/gif1.gif
docs/assets/gif2.gif
docs/assets/gif3.gif
curl -fsSL https://raw.githubusercontent.com/Alegau03/CTX/main/scripts/install.sh | sh
curl -fsSL https://raw.githubusercontent.com/Alegau03/CTX/main/scripts/install.sh | sh
curl -fsSL https://raw.githubusercontent.com/Alegau03/CTX/main/scripts/install.sh | sh
curl -fsSL https://raw.githubusercontent.com/Alegau03/CTX/main/scripts/install.sh | sh
curl -fsSL https://raw.githubusercontent.com/Alegau03/CTX/main/scripts/install.sh | sh
Gates applied: no_behavioural_pass, no_license.
711da03f8a33full audit observations/trust-audit/mcp-server/alegau03__ctx-3.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 | 711da03f8a33 | BLOCK | D | 69 | first audit |
Questions
What is the CTX MCP server?
CTX - Context Runtime Engine for Coding Agents
What tools does CTX expose?
15 in total: 11 read-only, 3 that write, and 1 that can delete or overwrite (memory_delete). Every one is listed on this page with its risk.
Is CTX safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does CTX need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (711da03f8a33), read on 2026-10-07. The repository is watched and re-audited when it changes.