CtxoBLOCK
MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git intent, blast radius, and change health in a single call. Works with any language deep analysis for TypeScript,Java, Go, and C#.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@ctxo/cli) [](https://github.com/alperhankendi/Ctxo/actions/workflows/ci.yml) [](https://github.com/alperhankendi/Ctxo/actions/workflows/release.yml)
npm install -g @ctxo/cli # one-time global install (gives you the `ctxo` command) ctxo init ctxo index
Detects your languages, installs the right plugins, wires Ctxo into your AI client, installs git hooks, and builds the first index one command.
The Problem: agents code blind
Drop a modern coding agent into a real repo. It ripgreps a symbol, gets 47 hits, reads five files to find the definition, five more for callers misses the subclass entirely (inheritance doesn't show up in text search), never checks git history (and confidently reintroduces a bug that was reverted three weeks ago), then runs out of context and starts hallucinating.
It's not a skill gap. It's a sensory gap. The agent is navigating your codebase with its eyes closed and a phone book.
The Solution: proactive, not reactive
The core shift: your agent stops reacting to files it stumbles into and starts planning from a complete map. Blast radius before the edit. Git intent before the bug fix. Importer list before the rename.
Ctxo indexes your repo onc
f288b5d84042OBSERVED · 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 site -- npx -y @ctxo/[email protected]
{
"mcpServers": {
"site": {
"command": "npx",
"args": [
"-y",
"@ctxo/[email protected]"
]
}
}
}Exposed tools (14)
14 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
find_dead_code | read | |
find_importers | read | |
get_architectural_overlay | read | |
get_blast_radius | read | |
get_change_intelligence | read | |
get_changed_symbols | read | |
get_class_hierarchy | read | |
get_context_for_task | read | |
get_logic_slice | read | |
get_pr_impact | read | |
get_ranked_context | read | |
get_symbol_importance | read | |
get_why_context | read | |
search_symbols | read |
Trust audit
BLOCKgrade F · trust 60/100 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) | WARN |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
visualization-payload.ts.json
visualization-payload.ts
exec(sql: string, params?: unknown[]): QueryExecResult[];
<div class="lang-dropdown" style="display:none;position:absolute;top:100%;right:0;margin-top:4px;flex-direction:column;gap:2px;min-width:200px;padding:6px;background:#ffffff;border:1px solid #e2e8f0;b
<span style="padding:2px 6px;font-size:0.6rem;font-weight:700;background:rgba(13,148,136,0.08);color:#0d9488;border:1px solid rgba(13,148,136,0.2);border-radius:10px;">NEW</span>
<div class="lang-dropdown" style="display:none;position:absolute;top:100%;right:0;margin-top:4px;flex-direction:column;gap:2px;min-width:200px;padding:6px;background:#ffffff;border:1px solid #e2e8f0;b
<span style="padding:2px 6px;font-size:0.6rem;font-weight:700;background:rgba(13,148,136,0.08);color:#0d9488;border:1px solid rgba(13,148,136,0.2);border-radius:10px;">NEW</span>
.gitlab-ci.yml
const hash = createHash('sha1');import { SqliteStorageAdapter } from '../../../packages/cli/src/adapters/storage/sqlite-storage-adapter.js';import { MaskingPipeline } from '../../../packages/cli/src/core/masking/masking-pipeline.js';import { SimpleGitAdapter } from '../../../packages/cli/src/adapters/git/simple-git-adapter.js';import { handleGetLogicSlice } from '../../../packages/cli/src/adapters/mcp/get-logic-slice.js';import { handleGetWhyContext } from '../../../packages/cli/src/adapters/mcp/get-why-context.js';private readonly endpoint = 'https://10.0.0.50:8443/api';
@ctxo/plugin-api, @types/node, tsup, typescript, vitest
@changesets/cli, tsx
@clack/prompts, @modelcontextprotocol/sdk, chokidar, graphology, graphology-communities-louvain, picocolors, picomatch, simple-git
tree-sitter, @types/node, tsup, typescript, vitest
tree-sitter, @types/node, tsup, typescript, vitest
- **NFR10:** Ctxo process runs with no elevated privileges; does not require sudo or admin rights
NFR10: Ctxo runs with no elevated privileges; does not require sudo or admin rights
- **NFR10:** Ctxo runs with no elevated privileges; does not require `sudo` or admin rights
edges, and per-symbol cyclomatic complexity. Because it has full access to the
- **Epic 8 (all 5 stories) — Webhook server for GitHub/GitLab.** Superseded by simpler model: `post-commit` git hook (installed by `ctxo init` in v0.5.0+) keeps index current locally, and `ctxo index
Gates applied: no_behavioural_pass.
f288b5d84042full audit observations/trust-audit/mcp-server/alperhankendi__ctxo.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 | f288b5d84042 | BLOCK | F | 60 | first audit |
Questions
What is the Ctxo MCP server?
MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git intent, blast radius, and change health in a single call. Works with any language deep analysis for TypeScript,Java, Go, and C#.
What tools does Ctxo expose?
14 in total: 14 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Ctxo safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (60/100) and found 3 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 Ctxo need?
No credential environment variables were found in its source, so it appears to need none.
How does Ctxo run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @ctxo/site at 0.0.0.
How current is this page?
The grade is for one exact copy of the source (f288b5d84042), read on 2026-10-07. The repository is watched and re-audited when it changes.