Deedglass
NPM · DEEDGLASS
Deedglass lets rules decide each AI agent tool call, checks what really changed and seals a record.
Available components
Last scanned (20 hours ago)
Scores higher than 69% of npm servers
Category Security
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
- No install/post-install scripts declared.Pass
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to deedglass/deedglass). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 6 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 546 tokens (~109/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: the tool surface changed between 0.1.1 and 0.15.0: 5 tool removals, 0 breaking changes, 5 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (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.
- 3 Nov 26 0
- Package version: 0.1.0 → 0.15.0 functional
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 0
- Malware scan: unverified → pass ▲ security
- Package version: 0.14.1 → 0.15.0 functional
- 27 Oct 26 0
- Malware scan: unverified → pass ▲ security
- Package version: 0.13.0 → 0.14.1 functional
- Package version: 0.13.0 → 0.14.0 functional
- 26 Oct 26 −15
- Known CVEs: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Dependency health: 1.00 → unverified ▼ functional
- Package version: 0.10.0 → 0.13.0 functional
- Package version: 0.10.0 → 0.12.0 functional
- Package version: 0.10.0 → 0.11.0 functional
- 25 Oct 26 −3
- Stability: 0.20 → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Stability: 0.20 → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Dependency health: 1.00 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
- Package version: 0.7.0 → 0.10.0 functional
- Package version: 0.1.0 → 0.9.0 functional
- Package version: 0.7.0 → 0.9.0 functional
- Package version: 0.7.0 → 0.8.0 functional
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +16
- Malware scan: unverified → pass ▲ security
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 npm/deedglass@0.15.0
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 | deedglass/deedglass |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/deedglass/deedglass/.github/workflows/release.yml@refs/tags/v0.15.0 |
| Rekor log index | 3535331047 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:b556e987ca29abafe193c9057caac424e130bd0ebcca7a57c16a56f6b5e66a0c4b577d9e64ffc27a93b87373f0a44694407682f44b7baf998f7301ae0 |
Background: How many MCP packages publish verified provenance →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| 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 →
deedglass_check_approval Check a Deedglass approval ~157
Checks whether a person has countersigned an action that Deedglass paused for approval. Call it with the approval_id from a 'Waiting for approval' message. It waits up to wait_seconds (0 to 20, default 10) for the decision, so one call is usually enough. If it was approved, Deedglass runs the original tool call and returns its result. Nothing runs while the approval is pending.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_id | string | yes | The approval id, for example apr_01j9zs4k7m2n3p5q6r7s8t9v0w |
| wait_seconds | integer | – | How long to wait for a person's decision before answering, in seconds. |
No output schema declared.
No examples provided.
postgres_call Call ~52
Call an allow-listed function with named arguments: public.ship_order(bigint): Mark a paid order shipped.
| Name | Type | Req | Description |
|---|---|---|---|
| args | object | – | The function's named arguments. |
| function | string | yes | An allow-listed function. |
No output schema declared.
No examples provided.
postgres_describe Describe ~55
List the tables the agent can read: columns, types, primary keys, row estimates, and which tables are writable and watched.
| Name | Type | Req | Description |
|---|---|---|---|
| schema | string | – | Only this schema. |
| table | string | – | Only this table. |
No output schema declared.
No examples provided.
postgres_execute Execute ~100
Run one INSERT, UPDATE, DELETE or MERGE in a transaction Deedglass controls, as a least-privilege role. Writable tables: public.orders, public.refunds.
| Name | Type | Req | Description |
|---|---|---|---|
| params | array | – | Values for $1, $2 …: strings, integers, booleans or null; at most 100. |
| sql | string | yes | One INSERT, UPDATE, DELETE or MERGE. Use $1, $2 … for values. |
No output schema declared.
No examples provided.
postgres_query Query ~105
Run one read-only SQL statement against public and get up to 500 rows back. Read-only: it never commits.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Return at most this many rows (default and maximum 500). |
| params | array | – | Values for $1, $2 …: strings, integers, booleans or null; at most 100. |
| sql | string | yes | One read-only SQL statement (SELECT). Use $1, $2 … for values. |
No output schema declared.
No examples provided.
How do I install the Deedglass MCP server?
Deedglass runs locally as an npm package, launched with npx -y deedglass. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · deedglass
claude mcp add deedglass-deedglass -- npx -y deedglass
What is the Deedglass MCP server?
Deedglass is an MCP server listed in the public MCP registry as io.github.deedglass/deedglass. Deedglass lets rules decide each AI agent tool call, checks what really changed and seals a record. This page covers its npm package (deedglass).
Is the Deedglass MCP server safe to use?
Deedglass scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 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 Deedglass MCP server expose?
Deedglass exposes 5 tools: postgres_call, postgres_describe, postgres_execute, postgres_query, deedglass_check_approval. Their descriptions and schemas cost roughly 469 tokens of context every time the server is loaded.
Is the Deedglass MCP server still maintained?
Deedglass is still listed as active in the MCP registry. We last reached this channel on 4 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 Deedglass MCP server under?
Deedglass 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.