KG-SSOT
MCPB · KG-SSOT-4.43.0.MCPB · 2 COMPONENTS
Company-brain knowledge graphs: confirmed claims cite sources, and decisions get revisited
Available components
Last scanned (11 hours ago)
Scores higher than 92% of MCPB servers
Category Memory and Knowledge
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 Security13
- 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 were checked across the 8 of 8 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- Install-script risk not yet assessed.Unverified
- 0 of 8 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to marciocar/kg-ssot). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability54
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2002 tokens (~222/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
- Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 63% 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 1 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 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.
- 4 Nov 26 −1
- Schema quality: 146 → 222 ▼ functional
- Schema quality: 146 → 172 ▼ functional
- Tool coverage: 55% → 63% ▲ functional
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 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 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.
- 30 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.
- 28 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.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
- Tool coverage: 64% → 53% ▼ functional
- Tool coverage: 64% → 47% ▼ functional
- Schema quality: pass → fail ▼ functional
- Destructive annotations: All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. 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/marciocar/kg-ssot/releases/download/kg-ssot-v4.43.0/kg-ssot-4.43.0.mcpb
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 | mcpb |
| Reason | Verified |
| Discovered via | GitHub artifact attestations |
| Source repo | marciocar/kg-ssot |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/marciocar/kg-ssot/.github/workflows/release.yml@refs/tags/kg-ssot-v4.43.0 |
| Rekor log index | 3691909169 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha256:36b43212a9ec309f181275031980e1e387195de02f9c1f828869f2d79bcb578a |
Background: How many MCP packages publish verified provenance →
Dependencies 8 packages
| Packages resolved | 8 |
|---|---|
| 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 →
kg_delete ~82
Removes a graph from the store, only if no graph that points to it fails without it.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_sha256 | string | – | – |
| message | string | – | – |
| name | string | yes | relative path in the store, ending in .kg.yaml or .kg.json (e.g. graphs/case.kg.yaml); the extension sets the text format |
No output schema declared.
No examples provided.
kg_get ~81
Reads a graph from the store (the text and the sha256). With ref, an earlier version (see kg_history).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | relative path in the store, ending in .kg.yaml or .kg.json (e.g. graphs/case.kg.yaml); the extension sets the text format |
| ref | string|integer | – | – |
No output schema declared.
No examples provided.
kg_history ~67
The operations on a graph in the store, newest first (ref, op, author, date).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | relative path in the store, ending in .kg.yaml or .kg.json (e.g. graphs/case.kg.yaml); the extension sets the text format |
No output schema declared.
No examples provided.
kg_list ~18
Lists the names of the graphs in the store.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
kg_query ~1,111
Queries the graphs in the store without judging: filters nodes by id, prefix, type, status, plane, layer, part of the graph name and words in the label; open=true returns the queue of open nodes; around returns the neighborhood of a node (name#id, or the unique id) by depth, edge type and direction. Each node comes with its outgoing and incoming edges and the other end resolved to its label (local or external, and whether it exists). Pages by cursor: repeat with next_cursor until it comes back null. group_by counts the nodes by field instead of listing them: use it for how many, per graph or per status. semantic orders by similarity to a question (needs the vector extra on the server); with text, both orders are fused by RRF. where also takes KEY^=VALUE (starts with) and KEY*=VALUE (contains), case-sensitive and on text only, and the degree counted from the internal edges of the node's own graph: degree.in.SUPPORTS=0 finds the nodes with no incoming internal SUPPORTS edge; a SUPPORTS from another graph is not counted, so to complete it list edges=true with where edge_type=SUPPORTS and scope=external. has and missing test whether any field is there, and null counts as missing. due=true lists what is overdue, the most overdue first. chain follows up to 50 ids back to their origin.
| Name | Type | Req | Description |
|---|---|---|---|
| around | string | – | – |
| as_of | string | – | with due, the date that counts as today |
| chain | array | – | the transmission chain from each id (name#id, or the unique id) back to its origin, up to 50 ids, by the edge types in edge_types (default TRACES_TO): one id gives kg-ssot.chain/1, more give kg-ssot.… |
| count_distinct | array | – | with group_by, count the distinct values (or combinations) of these fields in each group; null does not count |
| cursor | string | – | – |
| depth | integer | – | – |
| direction | – | – | – |
| due | boolean | – | only the nodes of any type whose verified_at plus reverify_every is due, the most overdue first, each with due_on and days_late; does not combine with sort=impact or semantic |
| edge_types | array | – | – |
| edges | boolean | – | count and list edges instead of nodes (internal and external); where and group_by then take edge_type, scope, file, meta.<key>, and from.<field> and to.<field> (id, file, found, node_type, status, pl… |
| fields | array | – | node keys that go out in extra, as globs: x_*, owner |
| graph | string | – | only the graphs whose name contains this text |
| group_by | array | – | count the nodes the filters find, by the value of each field, instead of listing them (kg-ssot.groups/2, every group, without pages): graph name as file, node_type, status, plane, layer, owner, label… |
| has | array | – | only the nodes that have these fields, any field, with a dot for a nested key (provenance.source); null counts as lacking it, and empty text and 0 count as having it |
| id_prefix | string | – | – |
| ids | array | – | – |
| in_narrative | boolean | – | – |
| layer | string | – | – |
| limit | integer | – | nodes per page (default 50) |
| min_count | integer | – | with group_by, keep only the groups with a count from this |
| missing | array | – | only the nodes that lack these fields, or have them as null |
| narrative | boolean | – | includes the narrative of each node |
| node_type | string | – | – |
| open | boolean | – | the queue of open nodes (status open) |
| plane | string | – | – |
| semantic | string | – | a question: orders the nodes by similarity to it (the vector extra); with text, fused by RRF |
| sort | – | – | – |
| status | string | – | – |
| text | string | – | words the label contains, all of them, case-insensitive |
| verified_before | string | – | no verified_at, or verified before the date |
| where | array | – | KEY=VALUE conditions, all of them: owner, an x_* field (a dot for a nested key), provenance.<key>, or the degree over internal edges: degree.in, degree.out or degree.total, with an optional edge type… |
No output schema declared.
No examples provided.
kg_schema_help ~52
The current contract for writing a graph that passes: the full MUST and SHOULD schemas, a minimal example that passes, the integrity rules and the fix for the most common codes. Call it before writing the first graph.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
kg_terms ~207
Resolves a domain term in the vocabulary of the store (the x_term profile, contract v4.11): text matches the preferred term or a synonym, ignoring case, accents and repeated spaces, and a synonym scoped to a case only matches with the same case. Each match carries the term, how it matched (pref, alt or hidden), whether that synonym is retired, the synonyms with source, document version, verification date and due date, and, for a superseded term, the terms that replace it. Use the term that replaces a superseded one, and treat a retired or due synonym as unconfirmed. Without text, lists the terms.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | – | the date for the due synonyms (today by default) |
| case | string | – | the case whose case-scoped synonyms count |
| limit | integer | – | terms or matches returned (default 50) |
| text | string | – | the text to resolve; without it, the terms are listed |
No output schema declared.
No examples provided.
kg_validate ~175
Judges a .kg.yaml graph (or .kg.json, with format json) against the current KG-SSOT contract without writing. Returns verdict PASS or FAIL and, per occurrence, code (stable), place, path, line, message and hint (the fix). Fix by the hints and judge again before writing.
| Name | Type | Req | Description |
|---|---|---|---|
| format | – | – | the text format: yaml (.kg.yaml, the default) or json (.kg.json, in the contract's JSON profile); with name, the default comes from the extension |
| limit | integer | – | occurrences returned (default 50) |
| name | string | – | the name the graph would have in the store (verifies the external end as if it were there) |
| text | string | yes | the whole document: YAML in a .kg.yaml, JSON in a .kg.json |
No output schema declared.
No examples provided.
kg_write ~177
Writes a graph to the store, only if the contract passes the candidate and the graphs that point to it. The format comes from the name: .kg.yaml is YAML and .kg.json is JSON. written=false carries reason (gate, conflict, not_judged) and the verdict. Use expected_sha256 (the sha256 of what you read, or 'new' for a new name) so you do not overwrite someone else's change.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_sha256 | string | – | – |
| message | string | – | – |
| name | string | yes | relative path in the store, ending in .kg.yaml or .kg.json (e.g. graphs/case.kg.yaml); the extension sets the text format |
| text | string | yes | the whole document: YAML in a .kg.yaml, JSON in a .kg.json |
No output schema declared.
No examples provided.
How do I install the KG-SSOT MCP server?
KG-SSOT 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, 36b43212a9ec309f181275031980e1e387195de02f9c1f828869f2d79bcb578a; the commands to do that are on this page. If it does not match, do not open it.
mcpb · kg-ssot-4.43.0.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
36b43212a9ec309f181275031980e1e387195de02f9c1f828869f2d79bcb578a
macOS / Linux
echo "36b43212a9ec309f181275031980e1e387195de02f9c1f828869f2d79bcb578a kg-ssot-4.43.0.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\kg-ssot-4.43.0.mcpb).Hash -eq "36b43212a9ec309f181275031980e1e387195de02f9c1f828869f2d79bcb578a"
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 KG-SSOT MCP server?
KG-SSOT is an MCP server listed in the public MCP registry as io.github.marciocar/kg-ssot. Company-brain knowledge graphs: confirmed claims cite sources, and decisions get revisited. This page covers its MCPB bundle (https://github.com/marciocar/kg-ssot/releases/download/kg-ssot-v4.43.0/kg-ssot-4.43.0.mcpb).
Is the KG-SSOT MCP server safe to use?
KG-SSOT scores 58 out of 100 on VerifyMCP. 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 KG-SSOT MCP server expose?
KG-SSOT exposes 9 tools: kg_validate, kg_write, kg_delete, kg_get, kg_list, and 4 more. Their descriptions and schemas cost roughly 1,970 tokens of context every time the server is loaded.
What licence is the KG-SSOT MCP server under?
KG-SSOT 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.