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
Aman 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
MCP server for the aman AI companion ecosystem — identity, tools, workflows, guardrails, evaluation
Quickstart
# 1 — run it from where its publisher ships it
npx -y @aman_asmuei/aman-mcp
# 2 — ask your agent something
> MCP server for the aman AI companion ecosystem — identity, tools, workflows, guardrails, evaluation
Aman is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
AMAll 2 servers
@aman_asmuei2 servers
2 categories
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 Aman 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 aman-mcp -- npx -y @aman_asmuei/aman-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
47 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.
Read the user
Takes no parameters.
Example callreturns →
Get a structured summary of the identity: AI name, user name, trust level, personality.
Takes no parameters.
Example callreturns →
Update the Session section of core.md with resume, active topics, and recent decisions.
Takes no parameters.
Example callreturns →
Update a specific section of core.md by heading name. Replaces the section content.
Takes no parameters.
Example callreturns →
Update the Dynamics section of core.md with current personality state. Call this to adapt tone based on time of day, session energy, or conversation signals.
Takes no parameters.
Example callreturns →
Generate a deterministic image generation prompt from the AI
Takes no parameters.
Example callreturns →
List all installed tools with their status (MCP vs manual).
Takes no parameters.
Example callreturns →
Search the tool registry by query string.
Takes no parameters.
Example callreturns →
Add a new tool to kit.md.
Takes no parameters.
Example callreturns →
Remove a tool from kit.md by name.
Takes no parameters.
Example callreturns →
List all defined workflows.
Takes no parameters.
Example callreturns →
Get a specific workflow
Takes no parameters.
Example callreturns →
Add a new workflow with named steps.
Takes no parameters.
Example callreturns →
Update the steps of an existing workflow by name.
Takes no parameters.
Example callreturns →
Remove a workflow by name.
Takes no parameters.
Example callreturns →
List all rule categories and their rules.
Takes no parameters.
Example callreturns →
Check if a proposed action might violate any rules. Returns matching violations.
Takes no parameters.
Example callreturns →
Add a new rule to a category. Creates the category if it doesn
Takes no parameters.
Example callreturns →
Remove a rule by 1-based index from a category.
Takes no parameters.
Example callreturns →
Toggle a rule
Takes no parameters.
Example callreturns →
Get current evaluation metrics: sessions count, trust level, trajectory, recent ratings.
Takes no parameters.
Example callreturns →
Log a session evaluation with rating and notes.
Takes no parameters.
Example callreturns →
Record a milestone achievement in the evaluation log.
Takes no parameters.
Example callreturns →
Get a full evaluation report with status, milestones, and summary.
Takes no parameters.
Example callreturns →
List all skills (installed and available from built-in registry).
Takes no parameters.
Example callreturns →
Search skills by name or description.
Takes no parameters.
Example callreturns →
Install a skill by name. Adds it to skills.md.
Takes no parameters.
Example callreturns →
Uninstall a skill by name. Removes it from skills.md.
Takes no parameters.
Example callreturns →
Read a text file and return its contents. Supports all common text formats (.txt, .md, .json, .js, .ts, .py, .html, .css, .yml, .sql, etc). For binary documents (.docx, .pdf), use doc_convert instead.
Takes no parameters.
Example callreturns →
Convert a binary document to readable text. Supports PDF (built-in) and DOCX (built-in). For PPTX, XLSX, images: install Docling (pip install docling) or use
Takes no parameters.
Example callreturns →
List files and directories at a given path. Shows file names with sizes. Hides hidden files and node_modules by default.
Takes no parameters.
Example callreturns →
Create a new active intention (niyyah). Use when Aman commits to a durable goal across sessions.
Takes no parameters.
Example callreturns →
Read a single intention by id.
Takes no parameters.
Example callreturns →
List intentions filtered by status (default: active) and/or horizon.
Takes no parameters.
Example callreturns →
Patch an intention
Takes no parameters.
Example callreturns →
Bump an intention
Takes no parameters.
Example callreturns →
Move an intention to complete or abandoned with a reason.
Takes no parameters.
Example callreturns →
Takes no parameters.
Example callreturns →
Create a new project at LRU position #1. Existing projects shift down; #11 evicts to off-list. Optional createdAt/lastTouchedAt support back-dating during migration of existing work.
Takes no parameters.
Example callreturns →
Read a single project by id (full body including sessionLog).
Takes no parameters.
Example callreturns →
List projects filtered by status and/or LRU membership. Default: active+inActiveList.
Takes no parameters.
Example callreturns →
Fast path — return the position-1 active project, or null. Used by SessionStart hook and
Takes no parameters.
Example callreturns →
Load a project by name or id (fuzzy match). Brings to position #1; restores from off-list. Returns disambiguation candidates if ambiguous.
Takes no parameters.
Example callreturns →
Bump an in-list project to position #1 and update lastTouchedAt. Returns null if project is off-list (use project_load instead).
Takes no parameters.
Example callreturns →
Append a timestamped session note to the project
Takes no parameters.
Example callreturns →
Transition project lifecycle to complete / abandoned / paused with reason. Frees LRU slot.
Takes no parameters.
Example callreturns →
Patch project metadata (name, niyyah, workspaces, linkedIntentionId). When linkedIntentionId changes, the linked intention
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. Aman 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 93 / 100
Release 0.9.2 · scanned 25 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 score93
Findings0 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestb7c1161ee0889f5ecf7b3d4b5498771940599275199218e357fc243734d16070
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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 digestb7c1161ee0889f5e
Scanned2026-08-25
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 0.9.2 — 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.
0.9.2
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 Aman 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.