MELRA
NPM · @MELRA/CLI
Local MCP runtime for policy-governed, verified agent actions with durable receipts.
Available components
Last scanned (3 hours ago)
Scores higher than 87% of npm servers
Category Developer Tools
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 Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 107 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to XAGI-Lab/melra). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 7 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability57
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1113 tokens (~101/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 27% 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 12 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
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 30 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.
- 28 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.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +4
- Stability: unverified → 0.27 ▲ functional
- 16 Oct 26 76
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 5 Nov 2026 · Analysed npm/@melra/cli@0.3.0-alpha.14
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 | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | XAGI-Lab/melra |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/XAGI-Lab/melra/.github/workflows/release.yml@refs/tags/v0.3.0-alpha.14 |
| Rekor log index | 3276305008 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:c2e5723019a8cff8411b76ecdc043b014e7f75da88fb48d977fdee354cd2906590ea5ebf304afaa983ff1bd1c6c8a7e8514db14ef901a7d84420826ef |
Background: How many MCP packages publish verified provenance →
Dependencies 107 packages
| Packages resolved | 107 |
|---|---|
| Stale | 30 |
| 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 →
melra_capabilities MELRA capabilities ~23
Discover available local execution capabilities, policy defaults, and runtime limits.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
melra_execute Execute a planned MELRA task ~95
Execute one previously planned task through policy, runtime, verification, and receipt generation. If melra_plan returned an approval challenge, pass its id and its exact phrase; the phrase is scoped to that one task and expires. Policy is re-evaluated here, so a plan made under a looser policy is still refused. Only reads are retried.
| Name | Type | Req | Description |
|---|---|---|---|
| approval | object | – | – |
| taskId | string | yes | – |
No output schema declared.
No examples provided.
melra_plan Plan a MELRA task ~361
Persist a bounded task, evaluate policy, and return any scoped approval challenge without executing. Nothing runs until melra_execute. A policy denial comes back as a normal result with status policy_blocked and a reason, not as an error. Any operation that is not a read needs requiredEvidence, and constraints must stay empty.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | object | – | – |
| constraints | array | – | Leave empty. Freeform prose cannot be enforced, so a non-empty array is denied with freeform_constraints_not_enforceable. Express real limits as forbiddenEffects, budget, or requiredEvidence. |
| forbiddenEffects | array | – | Effects this task must never take. Denied before the adapter runs, and honoured even in unhinged mode. |
| goal | string | yes | Why this task is being run, in one human-readable sentence. |
| identity | object | – | Who is asking, and on whose behalf. Recorded on the task and every receipt, and matched against policy.capabilities when the operator has issued grants. Omitted means the implicit local principal. |
| operation | – | yes | – |
| reconciliation | array | – | How to settle this effect if MELRA never learns whether it happened — a request that went out and was never answered, or a crash mid-flight. Read against the facts that were true before the call (ide… |
| requiredEvidence | array | – | Predicates that must hold after execution for the task to be verified_success. Required for any non-read operation: a mutation with none is denied with mutation_requires_evidence. An adapter that suc… |
No output schema declared.
No examples provided.
melra_receipt Read MELRA evidence ~34
Retrieve action receipts and the execution certificate.
| Name | Type | Req | Description |
|---|---|---|---|
| receiptId | string | – | – |
| taskId | string | – | – |
No output schema declared.
No examples provided.
melra_task_cancel Cancel a MELRA task ~27
Cooperatively cancel a running or pending task.
| Name | Type | Req | Description |
|---|---|---|---|
| taskId | string | yes | – |
No output schema declared.
No examples provided.
melra_task_status Inspect MELRA task status ~27
Read the current durable state of a task.
| Name | Type | Req | Description |
|---|---|---|---|
| taskId | string | yes | – |
No output schema declared.
No examples provided.
melra_workflow_advance Advance a MELRA workflow ~46
Execute one ready workflow scheduling wave through governed MELRA tasks.
| Name | Type | Req | Description |
|---|---|---|---|
| approvals | array | – | – |
| inputs | array | – | – |
| workflowId | string | yes | – |
No output schema declared.
No examples provided.
melra_workflow_cancel Cancel a MELRA workflow ~30
Cooperatively cancel nonterminal workflow nodes and their tasks.
| Name | Type | Req | Description |
|---|---|---|---|
| workflowId | string | yes | – |
No output schema declared.
No examples provided.
melra_workflow_control Pause, resume, or suspend a MELRA workflow ~54
Halt a running workflow without losing node state, or lift a halt. Node progress is untouched, so a resumed workflow continues where it stopped.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| workflowId | string | yes | – |
No output schema declared.
No examples provided.
melra_workflow_plan Plan a MELRA workflow ~34
Validate, preflight, encrypt, and persist a bounded workflow without executing it.
| Name | Type | Req | Description |
|---|---|---|---|
| definition | object | yes | – |
No output schema declared.
No examples provided.
melra_workflow_status Inspect a MELRA workflow ~26
Read the current durable workflow projection.
| Name | Type | Req | Description |
|---|---|---|---|
| workflowId | string | yes | – |
No output schema declared.
No examples provided.
How do I install the MELRA MCP server?
MELRA runs locally as an npm package, launched with npx -y @melra/cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @melra/cli
claude mcp add xagi-lab-melra -- npx -y @melra/cli
What is the MELRA MCP server?
MELRA is an MCP server listed in the public MCP registry as io.github.XAGI-Lab/melra. Local MCP runtime for policy-governed, verified agent actions with durable receipts. This page covers its npm package (@melra/cli).
Is the MELRA MCP server safe to use?
MELRA scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 MELRA MCP server expose?
MELRA exposes 11 tools: melra_capabilities, melra_plan, melra_execute, melra_task_status, melra_task_cancel, and 6 more. Their descriptions and schemas cost roughly 757 tokens of context every time the server is loaded.
Is the MELRA MCP server still maintained?
MELRA is still listed as active in the MCP registry. We last reached this channel on 5 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 MELRA MCP server under?
MELRA 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.