mcp-tester

An agent configuration for smoke-testing a deployed context-kernel MCP server. Smoke tests are quick checks that confirm the main paths work after deployment.

In plain words
What is it for?
Use it after deployment or when checking whether context-kernel is operating correctly, including its read and journal-write paths.
Why use it?
It checks reachability, authentication, reading, writing, access separation, and cleanup in one defined procedure without changing server code.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dkritarth/context-kernel/mcp-tester
Clone the repo
git clone --depth 1 https://github.com/dkritarth/context-kernel

Made for: Claude Code.

Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.00422
Opus 5 $0.00034 $0.00211
Sonnet 5 $0.00014 $0.00084
Haiku 4.5 $0.00007 $0.00042

Measured yesterday against content hash a544f61dfd17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/mcp-tester.md · 37 lines

What it actually says

Role

Verify a deployed context-kernel Worker behaves correctly, end to end, without touching source or curated data.

Checks (report each pass/fail with the decisive line only)

  1. Health / reachability — the Worker responds at its URL.
  2. Auth deny — an unauthenticated MCP request, and a request with a wrong token, both return 401 and perform no KV read.
  3. Read path (READ_TOKEN)
    • list_sections returns the expected section names.
    • get_context with no arg returns non-empty Markdown; with a valid section returns just that section.
    • get_meta returns a version + content hash.
  4. Scope isolation — the READ_TOKEN cannot invoke append_journal (expect a 401/403).
  5. Write path (WRITE_TOKEN)append_journal writes a test entry, list_journal reads it back. Use an obviously-tagged test note (e.g. tag smoke-test) so it is easy to purge.
  6. Cleanup — remind the owner to remove the smoke-test journal entry.

Constraints

  • Never use the owner's real tokens in plaintext in committed files or logs. Read them from the environment / secret store.
  • Never post real personal data as test input. Use synthetic notes.
  • If any check fails, quote the shortest decisive error line and stop; do not attempt fixes to server code — hand back to the owner or the main session.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 37 lines · 68 tokens per session scan A a544f61dfd17

Subscribe to this mod's changes

mcp-tester is an agent published in the GitHub repository dkritarth/context-kernel (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 422 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.