opchain
REMOTE · OPCHAIN.DEV · SCANNED SEP 20
Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability84
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 2566 tokens (~32/item across 80 items; 7 tools + 73 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 2 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 75% 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
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 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 opchain MCP server?
opchain is a hosted endpoint at https://opchain.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · opchain.dev
claude mcp add --transport http asfbay-bit-opchain-skills 'https://opchain.dev/mcp'
{
"mcpServers": {
"asfbay-bit-opchain-skills": {
"url": "https://opchain.dev/mcp"
}
}
} {
"servers": {
"asfbay-bit-opchain-skills": {
"type": "http",
"url": "https://opchain.dev/mcp"
}
}
} [mcp_servers.asfbay-bit-opchain-skills] url = "https://opchain.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"asfbay-bit-opchain-skills": {
"type": "remote",
"url": "https://opchain.dev/mcp",
"enabled": true
}
}
} openclaw mcp add asfbay-bit-opchain-skills --url 'https://opchain.dev/mcp' --transport streamable-http
mcp_servers:
asfbay-bit-opchain-skills:
url: "https://opchain.dev/mcp" {
"McpServers": {
"asfbay-bit-opchain-skills": {
"Transport": "http",
"Url": "https://opchain.dev/mcp"
}
}
} assistant mcp add asfbay-bit-opchain-skills -t streamable-http -u 'https://opchain.dev/mcp'
{
"mcpServers": {
"asfbay-bit-opchain-skills": {
"type": "http",
"url": "https://opchain.dev/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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 0
- Server version: f196207 → 8bad1a0 functional
- 18 Sept 26 0
- Server version: d4f926b → f196207 functional
- 15 Sept 26 0
- Server version: 5f06afd → d4f926b functional
- 14 Sept 26 0
- Tool “write_checkpoint” rewrote its description, which is the text the model reads security
- Schema quality: 40 → 32 ▲ functional
- New prompt “oc-enroll” functional
- New prompt “oc-evolve” functional
- New prompt “oc-hindsight” functional
- New prompt “oc-update” functional
- New prompt “oc-rev-spec” functional
- New resource “OC · API Developer reference manifest” functional
- New resource “OC · Agent Forge reference manifest” functional
- New resource “OC · App Architect reference manifest” functional
- New resource “OC · Bug Check reference manifest” functional
- New resource “OC · Checkpoint Protocol reference manifest” functional
- New resource “OC · Claude API reference manifest” functional
- New resource “OC · Code Auditor reference manifest” functional
- New resource “OC · Compliance Ops reference manifest” functional
- New resource “OC · Cost Ops reference manifest” functional
- New resource “OC · Dash Forge reference manifest” functional
- New resource “OC · Data Ops reference manifest” functional
- New resource “OC · Deploy Ops reference manifest” functional
- New resource “OC · Docs Forge reference manifest” functional
- New resource “OC · Evolve” functional
- New resource “OC · Evolve reference manifest” functional
- New resource “OC · Fleet Ops reference manifest” functional
- New resource “OC · Git Ops reference manifest” functional
- New resource “OC · Hindsight” functional
- New resource “OC · Hindsight reference manifest” functional
- New resource “OC · Integrations Engineer reference manifest” functional
- New resource “OC · Migration Ops reference manifest” functional
- New resource “OC · Modularize Ops reference manifest” functional
- New resource “OC · Monitoring Ops reference manifest” functional
- New resource “OC · Orchestrator reference manifest” functional
- New resource “OC · Prompt Ops reference manifest” functional
- New resource “OC · QA Ops reference manifest” functional
- New resource “OC · RAG Forge reference manifest” functional
- New resource “OC · Release Ops reference manifest” functional
- New resource “OC · Repo Ops reference manifest” functional
- New resource “OC · Reverse Spec reference manifest” functional
- New resource “OC · Scale Ops reference manifest” functional
- New resource “OC · Security Auditor reference manifest” functional
- New resource “OC · Security Hardening reference manifest” functional
- New resource “OC · Signal Forge reference manifest” functional
- New resource “OC · Stack Forge reference manifest” functional
- New resource “OC · Telemetry Ops reference manifest” functional
- New resource “OC · UX Engineer reference manifest” functional
- New resource “OC · Update” functional
- New resource “OC · Update reference manifest” functional
- Server version: f5e4b2a → 5f06afd functional
- Server version: 78567c2 → f5e4b2a functional
- “write_checkpoint” added an optional parameter “expectedRevision” cosmetic
- 5 Sept 26 0
- Server version: 244bf13 → 78567c2 functional
- 2 Sept 26 −3
- Stability: pass → fail ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “read_checkpoint” rewrote its description, which is the text the model reads security
- Schema quality: 1467 → 1646 ▼ functional
- “read_checkpoint” made “sessionId” required, so existing callers break ▼ functional
- “write_checkpoint” made “sessionId” required, so existing callers break ▼ functional
- Schema quality: excellent → good functional
- New prompt “oc-compliance” functional
- New prompt “oc-comply” functional
- New prompt “oc-data-ops” functional
- New prompt “oc-harden” functional
- New prompt “oc-qa” functional
- New resource “OC · Compliance Ops” functional
- New resource “OC · Data Ops” functional
- New resource “OC · QA Ops” functional
- New resource “OC · Security Hardening” functional
- Server version: f014746 → 244bf13 functional
- Server version: 395fc31 → f014746 functional
- New tool “create_checkpoint_session” functional
- “read_checkpoint” reworded the description of “sessionId” cosmetic
- “write_checkpoint” reworded the description of “sessionId” cosmetic
- 30 Aug 26 0
- Schema quality: good → excellent functional
- New prompt “oc-git-release” functional
- Server version: 57ef163 → 395fc31 functional
- 28 Aug 26 0
- Server version: 24b97be → 57ef163 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 20 Sept 2026 · Probed https://opchain.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=opchain.dev | CN=WE1,O=Google Trust Services,C=US | 20 Aug 2026 | 18 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | c023f38dc1089d9313d4e72548c005fd |
| SANs: opchain.dev, staging.opchain.dev, *.staging.opchain.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of opchain.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| opchain.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=(), usb=(), accelerometer=(), gyroscope=(), magnetometer=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://opchain.dev/mcp | Verified | 200 | |
| http (plaintext) | http://opchain.dev/mcp | HTTPS enforced | 301 | https://opchain.dev/mcp |
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 →
create_checkpoint_session ~40
Create a private server-issued session for checkpoint storage. Retain the returned sessionId and use it with read_checkpoint/write_checkpoint; never invent or share one.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_orchestrator ~37
Return the shared orchestrator protocol (welcome flow, pipeline map, active-chaining rules). Read once at the start of a session.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_skill ~62
Return the full SKILL.md (the instructions) for one skill id. Load it, then follow it. Read get_orchestrator once before your first get_skill in a session.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Skill id, e.g. oc-app-architect. |
No output schema declared.
No examples provided.
list_skills ~37
List every opchain skill (id, displayName, description, phases, commands). Call this first to see the concept→ship pipeline.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
read_checkpoint ~56
Read a skill's saved session checkpoint (where you left off). sessionId must be a private token returned by create_checkpoint_session.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | Private token returned by create_checkpoint_session. |
| skill | string | yes | – |
No output schema declared.
No examples provided.
route ~72
Map a request or an /oc-* command to the skill that should handle it, with the entry phase. Use when you're unsure which skill fits.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | An /oc-* command (e.g. /oc-discover) or a natural-language request (e.g. 'build me an app'). |
No output schema declared.
No examples provided.
write_checkpoint ~130
Persist a skill's session checkpoint so progress survives across sessions. Stores the object as given (any JSON object up to 64 KiB); it does not validate it against the opchain checkpoint protocol, so write the shape the protocol documents.
| Name | Type | Req | Description |
|---|---|---|---|
| checkpoint | object | yes | The checkpoint JSON to store (skill_state, next_actions, etc.). |
| expectedRevision | – | – | Local durable transport only: null creates only if absent; a revision updates only that revision. Omit for atomic unguarded replacement. |
| sessionId | string | yes | Private token returned by create_checkpoint_session. |
| skill | string | yes | – |
No output schema declared.
No examples provided.
What is the opchain MCP server?
opchain is an MCP server listed in the public MCP registry as io.github.asfbay-bit/opchain-skills. Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate. This page covers its hosted endpoint (https://opchain.dev/mcp).
Is the opchain MCP server safe to use?
opchain scores 79 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 opchain MCP server expose?
opchain exposes 7 tools: list_skills, route, get_skill, get_orchestrator, create_checkpoint_session, and 2 more. Their descriptions and schemas cost roughly 434 tokens of context every time the server is loaded.
Does the opchain MCP server require authentication?
No. We connected to opchain without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the opchain MCP server still maintained?
opchain 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.