A2A Governance Bridge MCP server. Tools: verify agent compliance, authorize a2a transaction, get trust registry. Built by MEOK AI Labs.
Free
Nothing to run from here
Promptlens is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
PromptLens — AI prompt analysis MCP server for Claude Desktop & Claude Code. Shows how AI reads your prompts with 5-axis scoring and 3-color interpretation reports.
Quickstart
# 1 — run it from where its publisher ships it
npx -y promptlens-mcp
# 2 — ask your agent something
> PromptLens — AI prompt analysis MCP server for Claude Desktop & Claude Code. Shows how AI reads your prompts with 5-axis scoring and
Promptlens is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
CPAll 1 server
cppis1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Promptlens as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add promptlens-mcp -- npx -y promptlens-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Analyze a prompt for quality. Two modes:
Takes no parameters.
Example callreturns →
List all PromptLens projects with their stats (prompt count, average score, trend).
Takes no parameters.
Example callreturns →
Create a new PromptLens project for organizing prompt history.
Takes no parameters.
Example callreturns →
Get prompt history entries for a project. Returns prompts with scores, tags, and timestamps.
Takes no parameters.
Example callreturns →
Add a prompt to history with optional score and tags. Use this to manually record prompts you want to track.
Takes no parameters.
Example callreturns →
Import conversations from Claude Desktop (conversations.json) or Claude Code (.jsonl). Creates one project per conversation or merges all into one project.
Takes no parameters.
Example callreturns →
Get overall PromptLens statistics: total projects, total prompts, average score, most used tags, score trend.
Takes no parameters.
Example callreturns →
Register or update your Anthropic API key for Claude API analysis mode. The key is stored locally in ~/.promptlens/settings.json. You can also set the preferred model.
Takes no parameters.
Example callreturns →
View current PromptLens settings: API key status, preferred model, active project, storage location. TRIGGER RULES — call this tool when: - User says
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Compare two prompt entries and show the diff: text changes, score changes, 5-axis score changes, and tag changes. Use this to see how a prompt improved between versions. When the user says
Takes no parameters.
Example callreturns →
Get the version chain (revision history) of a prompt. Returns all versions linked by parentId, from the original to the latest revision, with score changes between each version.
Takes no parameters.
Example callreturns →
Generate an HTML dashboard with charts for a project or all projects. Includes score trend line chart, 5-axis radar chart, grade distribution donut, tag statistics bar chart, and recent analysis table. The HTML file is saved to ~/.promptlens/ and can be opened in a browser. When the user says
Takes no parameters.
Example callreturns →
Export a project\
Takes no parameters.
Example callreturns →
Import a .promptlens.json file into PromptLens. Two modes:
Takes no parameters.
Example callreturns →
Advanced history query with filters: score range, grade, date range, tags (AND/OR), missing elements, version roots only. More powerful than get_history. When the user asks to find prompts by score, date, grade, tag, or missing element — e.g.
Takes no parameters.
Example callreturns →
Save a timestamped snapshot of a project\
Takes no parameters.
Example callreturns →
Analyze multiple prompts at once and return a ranked comparison table. Useful for evaluating prompt candidates or scoring existing prompts in bulk. TRIGGER RULES — call this tool when: 1. User says
Takes no parameters.
Example callreturns →
Generate an improved version of a previously analyzed prompt based on its analysis results (missingElements, axis scores). The improved version is optionally saved as a new version linked to the original via parentId. TRIGGER RULES — call this tool when: 1. Command suffix: user ends message with
Takes no parameters.
Example callreturns →
Repeatedly improve and re-analyze a prompt until a target score is reached or max iterations exceeded. Each iteration generates an improved version, analyzes it, and links it via parentId. TRIGGER RULES — call this tool when: 1. Command suffix: user ends message with
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Promptlens costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 96 / 100
Release 0.5.4 · scanned 26 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings4 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest6ad963c21cfb48cd0c8d609565991648afc80f87edad90e94fb6b1d23a78d8ee
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| analyze_prompt | no tags | |
| list_projects | no tags | |
| create_project | no tags | |
| get_history | no tags | |
| add_history_entry | no tags | |
| import_claude_conversations | no tags | |
| get_stats | no tags | |
| set_api_key | no tags | |
| get_settings | no tags | |
| set_active_project | no tags | |
| compare_prompts | no tags | |
| get_versions | no tags | |
| visualize_project | no tags | |
| export_project | no tags | |
| import_project | no tags | |
| query_history | no tags | |
| snapshot_project | no tags | |
| batch_analyze | no tags | |
| improve_prompt | no tags | |
| loop_improve | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest6ad963c21cfb48cd
Scanned2026-08-26
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 0.5.4 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.5.4
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Promptlens in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.