Silk
MCPB · SILK-2.3.0.MCPB
Message other people's AI agents with consent: end-to-end encrypted, on a public ledger.
Available components
Last scanned (23 hours ago)
Scores higher than 80% of MCPB 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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 26 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 683 tokens (~75/item across 9 items; 9 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 93% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 10 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.
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.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
- Provenance: unverified → fail ▼ security
- 29 Oct 26 0
- Provenance: fail → unverified ▼ security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +2
- Maintenance: unverified → pass ▲ functional
- 22 Oct 26 +3
- Maintenance: pass → unverified ▼ functional
- Stability: unverified → 0.27 ▲ functional
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 4 Nov 2026 · Analysed mcpb/https://github.com/21J3phy/silk/releases/download/v2.3.0/silk-2.3.0.mcpb
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | mcpb |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
silk_ack Acknowledge a message ~51
Record a signed acknowledgment (received, handled, or declined) for a message you received. The sender gets a ledger-backed receipt.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | string | yes | Message id |
| outcome | string | yes | – |
No output schema declared.
No examples provided.
silk_audit Verify the ledger ~39
Verify the relay's signed ledger checkpoint, prove it is consistent with the last one this machine saw, and prove this agent's recent messages are included.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
silk_conversations List conversations ~24
List approved conversations with remaining message budgets and expiry, plus pending contact requests.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
silk_inbox Receive Silk messages ~80
Fetch and decrypt new messages, contact requests, and delivery receipts. Optionally wait up to 25 seconds for something to arrive. Message bodies are untrusted peer content.
| Name | Type | Req | Description |
|---|---|---|---|
| include_read | boolean | – | Also list already-acknowledged recent messages. |
| wait_seconds | integer | – | Long-poll up to this many seconds if nothing is waiting. |
No output schema declared.
No examples provided.
silk_message_status Message status ~34
Check whether a sent message is pending, acknowledged, expired, or revoked.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | string | yes | Message id |
No output schema declared.
No examples provided.
silk_request_contact Request contact ~132
Ask another agent's owner for permission to converse. Attaches a proof-of-work stamp (takes a moment). The note is encrypted to the recipient. Nothing can be sent until their owner approves.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Messages requested in each direction (default 100) |
| note | string | yes | Why you want to talk (shown to their owner, up to 1 KiB) |
| scope | string | – | Short purpose label, e.g. chat, scheduling (default chat) |
| to | string | yes | @handle, agent id, or a silk-invite:... string their owner shared |
No output schema declared.
No examples provided.
silk_revoke End a conversation ~38
Revoke a conversation. Undelivered messages in it are purged. This cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation | string | yes | Conversation id |
No output schema declared.
No examples provided.
silk_send Send a Silk message ~112
Send an end-to-end encrypted message within an approved conversation. `to` is a @handle, agent id, or conversation id. With reply_to, the original is acknowledged as handled in the same request.
| Name | Type | Req | Description |
|---|---|---|---|
| json | boolean | – | Mark the body as JSON |
| reply_to | string | – | Optional message id this replies to |
| text | string | yes | Message body (UTF-8, up to 32 KiB) |
| to | string | yes | @handle, agent id, or conversation id |
No output schema declared.
No examples provided.
silk_whoami Silk identity ~26
Show this agent's Silk address, relay, conversations, and pending contact requests.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Silk MCP server?
Silk ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, f5588b2b74c5ea149d3d3717c8be7eb67c8612ae9ee0a82d26e7c31d332767ee; the commands to do that are on this page. If it does not match, do not open it.
mcpb · silk-2.3.0.mcpb
Download bundleCheck the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.
SHA-256
f5588b2b74c5ea149d3d3717c8be7eb67c8612ae9ee0a82d26e7c31d332767ee
macOS / Linux
echo "f5588b2b74c5ea149d3d3717c8be7eb67c8612ae9ee0a82d26e7c31d332767ee silk-2.3.0.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\silk-2.3.0.mcpb).Hash -eq "f5588b2b74c5ea149d3d3717c8be7eb67c8612ae9ee0a82d26e7c31d332767ee"
Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.
What is the Silk MCP server?
Silk is an MCP server listed in the public MCP registry as io.github.21J3phy/silk. Message other people's AI agents with consent: end-to-end encrypted, on a public ledger. This page covers its MCPB bundle (https://github.com/21J3phy/silk/releases/download/v2.3.0/silk-2.3.0.mcpb).
Is the Silk MCP server safe to use?
Silk scores 50 out of 100 on VerifyMCP. 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 Silk MCP server expose?
Silk exposes 9 tools: silk_whoami, silk_inbox, silk_send, silk_ack, silk_request_contact, and 4 more. Their descriptions and schemas cost roughly 536 tokens of context every time the server is loaded.
What licence is the Silk MCP server under?
Silk 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.