io.github.rishiatlan/claude-prompt-optimizer
NPM · CLAUDE-PROMPT-OPTIMIZER-MCP · SCANNED SEP 20
Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency22
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 200 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 656 tokens (~59/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.github.rishiatlan/claude-prompt-optimizer MCP server?
io.github.rishiatlan/claude-prompt-optimizer runs locally as an npm package, launched with npx -y claude-prompt-optimizer-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · claude-prompt-optimizer-mcp
claude mcp add rishiatlan-claude-prompt-optimizer -- npx -y claude-prompt-optimizer-mcp
{
"mcpServers": {
"rishiatlan-claude-prompt-optimizer": {
"command": "npx",
"args": [
"-y",
"claude-prompt-optimizer-mcp"
]
}
}
} {
"servers": {
"rishiatlan-claude-prompt-optimizer": {
"command": "npx",
"args": [
"-y",
"claude-prompt-optimizer-mcp"
]
}
}
} codex mcp add rishiatlan-claude-prompt-optimizer -- npx -y claude-prompt-optimizer-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"rishiatlan-claude-prompt-optimizer": {
"type": "local",
"command": [
"npx",
"-y",
"claude-prompt-optimizer-mcp"
],
"enabled": true
}
}
} openclaw mcp add rishiatlan-claude-prompt-optimizer --command npx --arg -y --arg claude-prompt-optimizer-mcp
mcp_servers:
rishiatlan-claude-prompt-optimizer:
command: "npx"
args: ["-y", "claude-prompt-optimizer-mcp"] {
"McpServers": {
"rishiatlan-claude-prompt-optimizer": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"claude-prompt-optimizer-mcp"
]
}
}
} assistant mcp add rishiatlan-claude-prompt-optimizer -t stdio -c npx -a -y claude-prompt-optimizer-mcp
{
"mcpServers": {
"rishiatlan-claude-prompt-optimizer": {
"command": "npx",
"args": [
"-y",
"claude-prompt-optimizer-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 −3
- Stability: pass → 0.83 functional
- 17 Sept 26 +1
- Stability: 0.97 → pass security
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +1
- Security disclosure: unverified → pass ▲ functional
- 10 Sept 26 −4
- Security disclosure: pass → unverified ▼ functional
- Stability: pass → 0.77 functional
- 9 Sept 26 +1
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/claude-prompt-optimizer-mcp@2.2.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
approve_prompt ~36
Approve the compiled prompt. Returns the final optimized prompt ready for use.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session ID from optimize_prompt |
No output schema declared.
No examples provided.
check_prompt ~54
Quick pass/fail check of a prompt. Returns score, top issues, and a suggestion. No compilation, no session.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Optional context |
| raw_prompt | string | yes | The prompt to check |
No output schema declared.
No examples provided.
compress_context ~57
Compress context (code, docs) by removing irrelevant sections. Returns pruned context with token savings.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | The context text to compress |
| intent | string | yes | What the task is about — used to determine relevance |
No output schema declared.
No examples provided.
configure_optimizer ~143
Configure optimizer behavior: mode, threshold, strictness, default target, ephemeral mode, session limits.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_compile | boolean | – | Auto-compile prompts |
| default_target | string | – | Default output target |
| ephemeral_mode | boolean | – | Ephemeral mode: sessions in-memory only |
| max_session_dir_mb | number | – | Max session directory size in MB |
| max_session_size_kb | number | – | Max session size in KB |
| max_sessions | number | – | Max session count |
| mode | string | – | Optimization mode |
| strictness | string | – | Strictness level |
| threshold | number | – | Quality threshold (0-100) |
No output schema declared.
No examples provided.
estimate_cost ~51
Estimate token count and cost across providers for any prompt text. No session needed.
| Name | Type | Req | Description |
|---|---|---|---|
| prompt_text | string | yes | The prompt text to estimate cost for |
| target | string | – | Target platform for model recommendations |
No output schema declared.
No examples provided.
get_usage ~22
Get current usage count, limits, remaining quota, and tier information.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
license_status ~27
Check current license status, tier, and expiry. Returns purchase link if no license is active.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
optimize_prompt ~93
Analyze a raw prompt, detect ambiguities, compile an optimized version, score quality, and estimate cost across providers. Returns a PreviewPack for review.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Optional context: repo info, file contents, preferences |
| raw_prompt | string | yes | The raw user prompt to optimize |
| target | string | – | Output target: claude (XML), openai (system/user), generic (markdown) |
No output schema declared.
No examples provided.
prompt_stats ~41
Get aggregated optimization statistics: total count, average score, top task types, estimated savings.
| Name | Type | Req | Description |
|---|---|---|---|
| period | string | – | Stats period (Phase A: lifetime only) |
No output schema declared.
No examples provided.
refine_prompt ~85
Refine a prompt by answering blocking questions or providing manual edits. Re-runs analysis and returns updated PreviewPack.
| Name | Type | Req | Description |
|---|---|---|---|
| answers | object | – | Answers to blocking questions: { question_id: answer } |
| edits | string | – | Manual edits or additional context to incorporate |
| session_id | string | yes | Session ID from optimize_prompt |
| target | string | – | Change output target |
No output schema declared.
No examples provided.
set_license ~47
Activate a Pro or Power license key. Validates the Ed25519 signature offline and unlocks the corresponding tier.
| Name | Type | Req | Description |
|---|---|---|---|
| license_key | string | yes | License key string (starts with po_pro_) |
No output schema declared.
No examples provided.
What is the io.github.rishiatlan/claude-prompt-optimizer MCP server?
io.github.rishiatlan/claude-prompt-optimizer is an MCP server listed in the public MCP registry as io.github.rishiatlan/claude-prompt-optimizer. Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium. This page covers its npm package (claude-prompt-optimizer-mcp).
Is the io.github.rishiatlan/claude-prompt-optimizer MCP server safe to use?
io.github.rishiatlan/claude-prompt-optimizer scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.rishiatlan/claude-prompt-optimizer MCP server expose?
io.github.rishiatlan/claude-prompt-optimizer exposes 11 tools: optimize_prompt, refine_prompt, approve_prompt, estimate_cost, compress_context, and 6 more. Their descriptions and schemas cost roughly 656 tokens of context every time the server is loaded.
Is the io.github.rishiatlan/claude-prompt-optimizer MCP server still maintained?
io.github.rishiatlan/claude-prompt-optimizer is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.rishiatlan/claude-prompt-optimizer MCP server under?
io.github.rishiatlan/claude-prompt-optimizer declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.