agent-maildir
PYPI · AGENT-MAILDIR
Durable, local mailbox tools for agents running in different command-line harnesses.
Available components
Last scanned (22 hours ago)
Scores higher than 69% of PyPI servers
Category Communication
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to shafty023/agent-maildir). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 12 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 530 tokens (~75/item across 7 items; 7 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage78
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 33% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "mailbox_publish" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 8 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 9 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 8 Nov 26 61
First indexed and scored.
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 21 Nov 2026 · Analysed pypi/agent-maildir@0.1.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | shafty023/agent-maildir |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/shafty023/agent-maildir/.github/workflows/release.yml@refs/tags/v0.1.1 |
| Rekor log index | 3749026144 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:710e085077dfc0ca7450d9c03173d17cb081d76ae611451c6179b9bd333eb242 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| 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 →
mailbox_ack ~62
Archive a handled message and send its sender an acknowledgement. Call only after the requested action is done, rejected, or deferred.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | – |
| message_id | string | yes | – |
| note | string | – | – |
| status | string | – | – |
No output schema declared.
No examples provided.
mailbox_bind ~49
Bind this session to a registered mailbox agent id so its messages are pushed here. Unread messages are delivered immediately.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | yes | Registered agent id, e.g. claude-reviewer |
No output schema declared.
No examples provided.
mailbox_inbox ~30
List unread (unacknowledged) messages for a bound agent.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | – |
No output schema declared.
No examples provided.
mailbox_join ~118
Join the mailbox as the holder of a role: register this client's agent id (<harness>-<role> by default), subscribe it to role.<role> and any project topics, and bind the MCP session. Claude Code can also confirm live push; other clients use the mailbox tools to poll.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Agent id override; defaults to claude-<role> |
| project | array | – | Project names to subscribe to as project.<name> |
| role | string | yes | Role this session holds, e.g. reviewer |
No output schema declared.
No examples provided.
mailbox_publish ~136
Send a message to a direct recipient, a topic, or both, from a bound agent. Use reply_to when answering a received message.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_no_subscribers | boolean | – | – |
| authority | string | – | – |
| body | object | – | JSON content, e.g. {summary, requestedAction, evidence} |
| broadcast | boolean | – | Send to every registered agent except the sender |
| from_agent | string | – | – |
| reply_to | string | – | – |
| subject | string | yes | – |
| to | array | – | Direct recipient agent ids |
| topic | string | – | – |
| type | string | – | – |
No output schema declared.
No examples provided.
mailbox_read ~36
Read one message in full by id, including already acknowledged ones.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | – |
| message_id | string | yes | – |
No output schema declared.
No examples provided.
mailbox_status ~31
Show which mailbox agents this session is bound to, their unread counts, the orchestrator lease, and live listeners.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the agent-maildir MCP server?
agent-maildir runs locally as a PyPI package, launched with uvx agent-maildir mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · agent-maildir
claude mcp add shafty023-agent-maildir -- uvx agent-maildir mcp
What is the agent-maildir MCP server?
agent-maildir is an MCP server listed in the public MCP registry as io.github.shafty023/agent-maildir. Durable, local mailbox tools for agents running in different command-line harnesses. This page covers its PyPI package (agent-maildir).
Is the agent-maildir MCP server safe to use?
agent-maildir scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 agent-maildir MCP server expose?
agent-maildir exposes 7 tools: mailbox_status, mailbox_join, mailbox_bind, mailbox_inbox, mailbox_read, and 2 more. Their descriptions and schemas cost roughly 462 tokens of context every time the server is loaded.
Is the agent-maildir MCP server still maintained?
agent-maildir is still listed as active in the MCP registry. We last reached this channel on 21 November 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 agent-maildir MCP server under?
agent-maildir declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the agent-maildir MCP server?
VerifyMCP ran 15 checks on agent-maildir, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about agent-maildir: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.