thinkhard.si prompt tools MCP server
si.thinkhard/prompt-toolsthinkhard.sistreamable-httpv1.3.0Scanned
669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices.
14 tools: 1 do something that can't be undone, 8 change things and 5 only read.
- Reads private data · 5
- Reads text others write · 3
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the thinkhard.si prompt tools MCP server can do
The thinkhard.si prompt tools MCP server is published by thinkhard.si, a domain the MCP Registry verified. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_agent_brief) and create or change data (8 tools: grade_prompt, estimate_ai_cost, fix_bad_answer, define_ai_term and 4 more), but cannot delete data. 5 tools only read.
5 tools read private data (search_prompts, get_prompt, list_collections and 2 more); 3 tools bring in text other people can write (search_prompts, lint_prompts and audit_library).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 1.3.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Can't be undone 1Claude Code: ask
check_agent_briefBefore a task goes to a coding agent (Claude Code, Codex, Cursor, GitHub Copilot or another), check the brief: what kind of task it is, which of the parts that kind needs are there…1 finding
Why it is in this group
- The description says "cannot be undone".
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "check_agent_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description says "cannot be undone".
Description, as the server wrote it Before a task goes to a coding agent (Claude Code, Codex, Cursor, GitHub Copilot or another), check the brief: what kind of task it is, which of the parts that kind needs are there (the outcome, where in the code, how to reproduce a bug, the command that proves it works, done-when, what must not change, what is out of scope, tests, when to stop and ask, what to hand back), and what is risky as written (steps that cannot be undone with no rule to stop, keys, vague goals, several jobs at once). Returns readiness out of 10, the brief rewritten with every gap marked, and a starter CLAUDE.md or AGENTS.md.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Check agent brief
Changes things 8Claude Code: ask
build_assistantWrite the instructions for an assistant that keeps its rules: a ChatGPT custom GPT, a Claude Project, a Gemini Gem, a Microsoft Copilot agent or an app's system prompt.1 finding
Why it is in this group
- The description's first verb is "write": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "build_assistant" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "write": a word for a change.
Description, as the server wrote it Write the instructions for an assistant that keeps its rules: a ChatGPT custom GPT, a Claude Project, a Gemini Gem, a Microsoft Copilot agent or an app's system prompt. From what it is for and who will use it, it finds the tasks it will do in the repository and what each needs, picks the protections those users call for (scope, no promises the facts do not allow, no personal data, confirmation before acting, instructions a message cannot change), and returns the instructions, a name and description, first messages, files to attach, tools to switch on and five test requests.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Build assistant
check_answerDid the AI do what the prompt asked?No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Did the AI do what the prompt asked? Give the prompt and the answer it got. Finds every rule in the prompt that can be checked by reading (length in words, characters, sentences or lines, how many items, a list, a table and its columns, JSON and its keys, sections, plain text, what to include, start or end with, sign off as, what to leave out, no introduction, the language and spelling, first person, plain words, asking first, marking what is missing) and says for each whether the answer kept or broke it, with where. Also lists numbers, names, links and quotes in the answer that the prompt never gave it, which is where made-up facts hide, and for each broken rule the line that makes it hold. Use it before an AI answer is used or sent, and to make a prompt more reliable.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Check answer
define_ai_termPlain-English definitions of 102 AI words from the thinkhard.si glossary (token, context window, hallucination, temperature, system prompt, RAG, fine-tuning, agent, MCP and more), …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Plain-English definitions of 102 AI words from the thinkhard.si glossary (token, context window, hallucination, temperature, system prompt, RAG, fine-tuning, agent, MCP and more), written for people who use AI at work rather than build it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Define AI term
estimate_ai_costEstimate the monthly cost of running a prompt on current AI models (Claude, GPT, Gemini, DeepSeek, Qwen and others), from thinkhard.si's price catalog, which is checked against eac…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estimate the monthly cost of running a prompt on current AI models (Claude, GPT, Gemini, DeepSeek, Qwen and others), from thinkhard.si's price catalog, which is checked against each provider's pricing page. Give token counts, or paste the prompt text to estimate them.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Estimate AI cost
fix_bad_answerWhen an AI answer goes wrong (it made up a source or a number, ignored an instruction, came back too long or in the wrong shape, sounded robotic or generic, changed every time, ref…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it When an AI answer goes wrong (it made up a source or a number, ignored an instruction, came back too long or in the wrong shape, sounded robotic or generic, changed every time, refused, or lost track of a long chat), find the likely cause and the exact line to add to the prompt. Draws on the thinkhard.si troubleshooter of 33 common problems. Describe what went wrong in plain words.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Fix a bad answer
grade_promptScore a prompt out of 10 on the ten checks thinkhard.si uses (what to make, who it is for, background facts, length, format, what to avoid, what good looks like, an example, what t…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Score a prompt out of 10 on the ten checks thinkhard.si uses (what to make, who it is for, background facts, length, format, what to avoid, what good looks like, an example, what to do if unsure, layout for the model). Returns which checks pass and a plain question for each one that fails. It also reads the prompt against the expert prompts in the repository: which task it is, which of that task's inputs are there (a resume, a job posting, a policy), how ready it is for that task out of 10, and the three changes that would help most. Use it to see what a prompt is missing before improving it. The prompt is read to answer and is not stored.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Grade prompt
lint_promptsFind the prompts in source files (Python, JavaScript, TypeScript, YAML, JSON and prompt files) and review each for what breaks AI features in production: user input in a system pro…Reads private dataReads text others write1 finding
Why it is in this group
- The description's first verb is "find": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- private-dataThe description's first sentence says "find" and "file": it reads files.
- private-dataThe input names a file (input.files), and the tool reads: it reads files.
- untrusted-inputThe description's first sentence says "find" and "review": it reads comments, which other people can write.
Findings
- Warn
The server marks "lint_prompts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "find": a word for reading.
Description, as the server wrote it Find the prompts in source files (Python, JavaScript, TypeScript, YAML, JSON and prompt files) and review each for what breaks AI features in production: user input in a system prompt or with nothing around it, no rule that user text is data, code that parses the reply as JSON when the prompt never asks for JSON, a long fixed part after the changing part (so it cannot be cached), keys and personal data in prompts, and model ids that are not in the current catalog. Each finding has a line and a fix. Use it when writing or reviewing code that calls a model.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Lint prompts
plan_workflowTurn a job such as hiring for a role, launching a feature, closing the month or applying for a job into steps in the order the work happens, each with the expert prompt from the re…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Turn a job such as hiring for a role, launching a feature, closing the month or applying for a job into steps in the order the work happens, each with the expert prompt from the repository that does it, which earlier answer it takes and into which blank, and the details to gather once for all of them. Works from a one-line description (matched to a playbook of how that kind of work goes) or from steps listed one per line. Use it when a request is too big for one prompt; each step names the prompt to open with get_prompt.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Plan workflow
Only reads 5Show 5 read-only tools
audit_libraryRead many prompts at once, such as a team's shared prompt doc: each prompt's score on the ten checks, the task it does and how ready it is for it, near-copies with the one to keep,…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Read many prompts at once, such as a team's shared prompt doc: each prompt's score on the ten checks, the task it does and how ready it is for it, near-copies with the one to keep, private details that should not be in a shared prompt (emails, phone numbers, card numbers, keys), which collections the library covers and the expert prompts it lacks, a health score, and which prompts to fix first.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Audit library
get_promptGet the full text of one prompt from the thinkhard.si repository by its slug, registry number (such as CAR-001) or exact title, with its {{blanks}}, what goes in each, and why it w…Reads private dataNo findings
Why it is in this group
- The name "get_prompt" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "repository": it reads repositories.
Description, as the server wrote it Get the full text of one prompt from the thinkhard.si repository by its slug, registry number (such as CAR-001) or exact title, with its {{blanks}}, what goes in each, and why it works. If the name does not match exactly, it answers with the closest matches instead. Pass values to fill blanks with the user's details; blanks left without a value are listed in open_blanks.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get prompt
get_prompt_patternThe 24 prompt patterns from thinkhard.si: small moves that change the answer, such as giving the facts, naming the reader, showing one example, setting a length, fencing off pasted…No findings
Why it is in this group
- The name "get_prompt_pattern" says "get": a word for reading.
Description, as the server wrote it The 24 prompt patterns from thinkhard.si: small moves that change the answer, such as giving the facts, naming the reader, showing one example, setting a length, fencing off pasted text or asking for reasoning first. Each comes with when it helps, when it does not, a before-and-after pair with scores, and the line to add. Ask by a pattern's name or by what you want the prompt to do better; leave the query empty to list all 24.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get prompt pattern
list_collectionsList the collections in the thinkhard.si prompt repository, with how many prompts each has.Reads private dataNo findings
Why it is in this group
- The name "list_collections" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "repository": it reads repositories.
Description, as the server wrote it List the collections in the thinkhard.si prompt repository, with how many prompts each has.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List collections
search_promptsSearch the thinkhard.si repository of 1,274 tested prompt templates for work tasks: email, meetings, presentations, job search, marketing, sales, support, HR, finance, legal, sprea…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_prompts" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "repository": it reads repositories.
- untrusted-inputThe description's first sentence says "search" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Search the thinkhard.si repository of 1,274 tested prompt templates for work tasks: email, meetings, presentations, job search, marketing, sales, support, HR, finance, legal, spreadsheets, research and more. Use it when the user wants a prompt for something to write, plan, summarize, analyze or draft at work. Returns the best matches first, each with the slug that get_prompt takes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Search prompts
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:24 UTC, unchanged since Nov 7, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://thinkhard.si/mcp: tools/list returned 14 tools to an anonymous client, including check_agent_brief (irreversible), grade_prompt (write), estimate_ai_cost (write), fix_bad_answer (write), define_ai_term (write) and 4 more
Posture changes
- Nov 7, 2026
- Tools that change things, listed without credentials: 4 to 9
- Oct 30, 2026
- Tools that change things, listed without credentials: 2 to 4
Findings
Matches of fixed checks, with the text they matched.
- Warnbuild_assistant
The server marks "build_assistant" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "write": a word for a change.
- Warnlint_prompts
The server marks "lint_prompts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "find": a word for reading.
The server marks "check_agent_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description says "cannot be undone".
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:get_promptOnly readsdescription
- Changed:plan_workflowChanges thingsdescription
- Changed:search_promptsOnly readsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 9.View diff
- Tools that change things, listed without credentials: 4 to 9
Tools6 added, 6 changed.+6 added~6 changedView diff
- Added:audit_libraryOnly reads
- Added:build_assistantChanges things
- Added:check_agent_briefCan't be undone
- Added:check_answerChanges things
- Added:lint_promptsChanges things
- Added:plan_workflowChanges things
- Changed:define_ai_termChanges thingsdescriptioninputSchema
- Changed:estimate_ai_costChanges thingsinputSchema
- Changed:fix_bad_answerChanges thingsinputSchema
- Changed:get_prompt_patternOnly readsinputSchema
- Changed:grade_promptChanges thingsdescription
- Changed:search_promptsOnly readsinputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 4.View diff
- Tools that change things, listed without credentials: 2 to 4
Tools3 added, 1 changed.+3 added~1 changedView diff
- Added:define_ai_termChanges things
- Added:fix_bad_answerChanges things
- Added:get_prompt_patternOnly reads
- Changed:search_promptsOnly readsdescriptioninputSchema
Tools1 changed.~1 changedView diff
- Changed:get_promptOnly readsdescriptioninputSchema
Install
Pinned to version 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http prompt-tools https://thinkhard.si/mcpclaude mcp add --transport http prompt-tools https://thinkhard.si/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__prompt-tools__search_prompts",
"mcp__prompt-tools__get_prompt",
"mcp__prompt-tools__list_collections",
"mcp__prompt-tools__get_prompt_pattern",
"mcp__prompt-tools__audit_library"
],
"ask": [
"mcp__prompt-tools__grade_prompt",
"mcp__prompt-tools__estimate_ai_cost",
"mcp__prompt-tools__fix_bad_answer",
"mcp__prompt-tools__define_ai_term",
"mcp__prompt-tools__check_answer",
"mcp__prompt-tools__build_assistant",
"mcp__prompt-tools__plan_workflow",
"mcp__prompt-tools__lint_prompts",
"mcp__prompt-tools__check_agent_brief"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as prompt-tools. Review it before you use it.
Capability tags behind 5 rules
- mcp__prompt-tools__search_prompts private-data, untrusted-input
- mcp__prompt-tools__get_prompt private-data
- mcp__prompt-tools__list_collections private-data
- mcp__prompt-tools__lint_prompts private-data, untrusted-input
- mcp__prompt-tools__audit_library private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/si.thinkhard/prompt-tools/verify?hash=1dc5de635ca9b06ffbdda9bc45b87a16b13563de1d12281c629eb2c7c49ac444" | jq -e '.changed == false'Pinned hash 1dc5de635ca9, from Nov 18, 2026, 11:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/si.thinkhard/prompt-tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/si.thinkhard/prompt-tools)Source: MCP Registry. Synced Nov 4, 2026, 17:18 UTC.
thinkhard.si prompt tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the thinkhard.si prompt tools MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 9 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the thinkhard.si prompt tools MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the thinkhard.si prompt tools MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: check_agent_brief.
What tools does the thinkhard.si prompt tools MCP server have?
- 14 tools: 1 irreversible, 8 write, 5 read. check_agent_brief, grade_prompt, estimate_ai_cost, fix_bad_answer, define_ai_term, check_answer, build_assistant, plan_workflow and 6 more.
Does the thinkhard.si prompt tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the thinkhard.si prompt tools MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the thinkhard.si prompt tools MCP server changed its tools?
- Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.