Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Agent Blueprint
Agent Blueprint
by agentblueprint.ai · https://agentblueprint.ai/mcp
Measured agent costs, a one-page agent summary check, and an offline access map. No sign-in.
11 of 11 checks · 3 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 4 tools
- Its own safety labels
- 4 read-only
- Memory it takes
- About 1,600 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 9.6 KB in our test
- Speed
- Average answer in our test: 88 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 3 Nov 2026.
Is Agent Blueprint MCP server safe?
- None of the hidden-instruction wordings we know were found in its 4 tool descriptions.
- Its error messages showed no secrets or internal details.
- All 4 of its tools are labeled read-only.
- Overall it scored 93/100 on 3 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
None found in GitHub Security Advisories on 3 Nov 2026.
That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.
What it can do
4 tools, in the server's own words.
list_benchmark_jobsread-onlyLists the ten everyday jobs in Agent Blueprint's measured agent cost benchmark (2 November 2026): what each job was, how big its input was, and the typical and…
estimate_agent_costread-onlyEstimates the tokens and dollar cost of an AI agent task from the measured benchmark job closest to it.
check_agent_one_pageread-onlyChecks the structure of a one-page agent summary written from Agent Blueprint's template (https://agentblueprint.ai/agent-one-page-template): all eight section…
render_agent_mapread-onlyTurns an agent's own inventory of its connections into Agent Blueprint's one-page access map: a single offline HTML page showing what the agent can read and ch…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Every tool is describednote
1 warning
- !render_agent_map: Inputs with no description: version, agent, drawn, connections, checks, unseen, trim
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !3 tools answer with structured data but don't declare its shape (outputSchema): list_benchmark_jobs, estimate_agent_cost, check_agent_one_page. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
- ✓ConnectsConnected in 271 mspass
- ✓Ready for the newest MCP versionUses the latest MCP version (2026-07-28)pass
- ✓Lists its toolsFound 4 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Tools work with good inputspass
All good
- ✓list_benchmark_jobs: Worked (108 ms)
- ✓estimate_agent_cost: Worked (81 ms)
- ✓check_agent_one_page: Worked (83 ms)
- ✓render_agent_map: Answered with an error, probably because of our sample input: Input validation error: Invalid arguments for tool render_agent_map: drawn: Use YYYY-MM-DD.
- ✓Bad inputs give a clean errorpass
All good
- ✓list_benchmark_jobs: Refused wrong type for "agent" with a clear error
- ✓estimate_agent_cost: Refused missing required input "job" with a clear error
- ✓estimate_agent_cost: Refused wrong type for "job" with a clear error
- ✓check_agent_one_page: Refused missing required input "markdown" with a clear error
- ✓check_agent_one_page: Refused wrong type for "markdown" with a clear error
- ✓render_agent_map: Refused missing required input "version" with a clear error
- ✓render_agent_map: Refused wrong type for "version" with a clear error
- ✓Fast enoughpass
All good
- ✓Connecting took 271 ms
- ✓Listing tools took 255 ms
- ✓Average tool answer: 88 ms
- ✓list_benchmark_jobs: Slowest tool: list_benchmark_jobs (108 ms)
- ✓No secrets leakedChecked 8 error messages: no secrets or internal detailspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://agentblueprint.ai/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/ai-agentblueprint-agent-blueprint.html)Score over time
- 3 Nov 202693
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Agent Blueprint, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works