AccInt
MCPB · ACC-MCP-V0.1.12-X86_64-UNKNOWN-LINUX-MUSL.MCPB · 4 COMPONENTS
Local Work Model MCP server for agent work that learns from real outcomes.
Last scanned (15 hours ago)
Scores higher than 74% 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 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 & Transparency35
- 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
- License check failed: the license (LicenseRef-AccInt-EULA) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 137 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability54
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1745 tokens (~872/item across 2 items; 2 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 Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% 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 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
- Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
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.
- 4 Nov 26 −2
- Stability: pass → 0.83 functional
- 3 Nov 26 +1
- Maintenance: unverified → pass ▲ functional
- 2 Nov 26 +1
- Provenance: unverified → fail ▼ security
- Security disclosure: unverified → pass ▲ functional
- 1 Nov 26 −2
- Provenance: fail → unverified ▼ security
- Security disclosure: pass → unverified ▼ functional
- Maintenance: pass → unverified ▼ functional
- 29 Oct 26 0
- Stability: 0.97 → pass security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 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 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
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 mcpb/https://github.com/maxbaluev/accreted-intelligence/releases/download/v0.1.12/acc-mcp-v0.1.12-x86_64-unknown-linux-musl.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 →
acc_act ~953
DO anything. runtime: 'solve' (run a goal/sub-goal through the RLM loop — the Work Model (scored memory) first, then the reasoner; decomposition emerges; records an OPEN COMMITMENT and returns its `commitment` id; input=the goal; a solve may return `{kind:"brain_frame", frame:{…}, commitment:"solved:…"}` — an OPEN continuation frame for YOU to reason over and answer via 'continue'; the commitment id is bound at frame-open and checkpoints waiting if the frame expires) | 'continue' (submit your reasoned proposal back into an open brain continuation frame; input=JSON {frame_id, proposal_text} — frame_id IS the credential; submit_token OPTIONAL, verified when present (do NOT retype it: omitting beats transcribing); an identical duplicate submit replays the cached result) | 'outcome' (close a commitment with a REAL-WORLD verdict — immediate OR late, e.g. a reply lands days later or a deal closes — so credit flows to the exact knowledge the action relied on; input=JSON {ref|goal, good:bool, note?}) | 'exec' (run sandboxed code; inside it `acc --db /tmp/acc.db retrieve "<q>"` recurses over the memory) | 'register' (store named code, input=JSON {name,code}) | a registered runtime name (input -> $ACC_INPUT). BUILT-IN RUNTIME PRIORITY: for web browsing, page reads, web extraction, computer-use, profile/dashboard work, or logged-in browser actions, use runtime='browser' via acc_act('browser', JSON). `runtime:browser` drives acc's persistent logged-in Camoufox and is scored/compounded by grounded verification; when `profile` is omitted, URL/host/domain/surface/service hints, nested args, and code URL literals infer an existing site profile, explicit `profile` always wins, multiple matching profiles require explicit choice, and when no site profile exists, the persistent default profile is used. Do NOT use a clean default profile when a logged-in site profile exists, and do NOT use host-native browser tools (chrome-devtools, agent-browser) or curl for browser work when this run…
| Name | Type | Req | Description |
|---|---|---|---|
| input | string | yes | – |
| runtime | string | – | – |
No output schema declared.
No examples provided.
acc_retrieve ~160
Peek the Work Model — the scored-token memory — by MaxSim (late interaction). Returns ranked hits with bodies. The only READ primitive. Input is an object with optional `query` XOR `image`: pass `{"query":"<text>"}` for a TEXT retrieve, OR `{"image":"<file path or data: URI>"}` to LOOK at an image and retrieve knowledge CROSS-MODALLY (a text-trained memo answers an image). EXACTLY ONE of query|image — neither nor both is rejected.
| Name | Type | Req | Description |
|---|---|---|---|
| image | string | – | Path or data URI to LOOK at cross-modally. Supply image OR query, never both. |
| query | string | – | Text query for a normal memory retrieve. Supply query OR image, never both. |
No output schema declared.
No examples provided.
How do I install the AccInt MCP server?
AccInt 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. The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check the download against.
mcpb · acc-mcp-v0.1.12-x86_64-unknown-linux-musl.mcpb
Download bundleThe MCP registry declares no SHA-256 for this bundle, so there is no published digest to check it against. Open it with an MCPB-capable host such as Claude Desktop.
What is the AccInt MCP server?
AccInt is an MCP server listed in the public MCP registry as io.github.maxbaluev/accint. Local Work Model MCP server for agent work that learns from real outcomes. This page covers its MCPB bundle (https://github.com/maxbaluev/accreted-intelligence/releases/download/v0.1.12/acc-mcp-v0.1.12-x86_64-unknown-linux-musl.).
Is the AccInt MCP server safe to use?
AccInt scores 43 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 AccInt MCP server expose?
AccInt exposes 2 tools: acc_act, acc_retrieve. Their descriptions and schemas cost roughly 1,113 tokens of context every time the server is loaded.
What licence is the AccInt MCP server under?
AccInt declares the LicenseRef-AccInt-EULA licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.