Paper Chaser MCP
OCI · GHCR.IO/JOSHUASUNDANCE-SWCA/PAPER-CHASER-MCP:0.2.2
MCP server for academic papers, citations, authors, ECOS dossiers, and Federal Register text.
Available components
Last scanned (22 hours ago)
Scores higher than 93% of OCI servers
Category Education and Research
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: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result. View diagnostics → Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
Provenance & Transparency48
- 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
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 215 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).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 679 tokens (~113/item across 6 items; 5 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage82
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 45% 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 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
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.
- 31 Oct 26 0
- Provenance: unverified → fail ▼ security
- Security disclosure: unverified → pass ▲ functional
- 30 Oct 26 0
- Provenance: fail → unverified ▼ security
- Security disclosure: pass → unverified ▼ functional
- 20 Oct 26 0
- Stability: 0.97 → pass security
- 19 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 +2
- Stability: 0.87 → pass security
- 15 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.
- 14 Oct 26 −3
- Stability: pass → 0.80 functional
- 13 Oct 26 0
- Stability: 0.97 → 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 oci/ghcr.io/joshuasundance-swca/paper-chaser-mcp:0.2.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 299 ungraded findings
From the publisher's SBOM, not graded. These advisories match packages listed in the SBOM the publisher attached to this image. A publisher naming a vulnerable package in their own image is credible, so we show them. Nothing verifies that SBOM, though, so the Known CVEs signal does not grade the image from it.
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-2fqr-mr3j-6wp8 | CVE-2026-54279 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-2g87-pp6c-29x5 | high | yes | ||
| GHSA-494j-54xm-rwp3 | CVE-2026-111063 | medium | yes | |
| GHSA-4fvr-rgm6-gqmc | CVE-2026-54273 | medium | yes | |
| GHSA-4m7w-qmgq-4wj5 | CVE-2026-54275 | low | yes | |
| GHSA-5wr8-gcqf-gqf3 | CVE-2026-111064 | high | yes | |
| GHSA-63hw-fmq6-xxg2 | CVE-2026-54277 | medium | yes | |
| GHSA-6cjc-53gc-5rqm | CVE-2026-111065 | medium | yes | |
| GHSA-9x8q-7h8h-wcw9 | CVE-2026-54280 | low | yes | |
| GHSA-9xw5-w5jj-pvcg | CVE-2026-111066 | high | yes | |
| GHSA-cq5v-8q36-5273 | CVE-2026-69244 | high | yes | |
| GHSA-f9xw-jh8m-3mwq | CVE-2026-111748 | medium | yes | |
| GHSA-g3cq-j2xw-wf74 | CVE-2026-54278 | medium | yes | |
| GHSA-gx76-c99x-2c96 | CVE-2026-111749 | low | yes | |
| GHSA-hg6j-4rv6-33pg | CVE-2026-47265 | medium | yes | |
| GHSA-hpj7-wq8m-9hgp | CVE-2026-54276 | medium | yes | |
| GHSA-jg22-mg44-37j8 | CVE-2026-34993 | medium | CVSS:3.1/AV:L/AC:H/PR:H/UI:R/S:C/C:L/I:H/A:L | yes |
| GHSA-m6qw-4cw2-hm4m | CVE-2026-50269 | low | yes | |
| GHSA-mfx4-hv73-q22v | CVE-2026-69243 | medium | yes | |
| GHSA-mq44-7p77-q5h7 | CVE-2026-59881 | medium | yes | |
| GHSA-pqxq-w44r-73xw | CVE-2026-111750 | medium | yes | |
| GHSA-xcgm-r5h9-7989 | CVE-2026-54274 | medium | yes | |
| PYSEC-2026-2104 | CVE-2026-34993 | high | CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-2105 | CVE-2026-47265 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| PYSEC-2026-2106 | CVE-2026-50269 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2107 | CVE-2026-54273 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2108 | CVE-2026-54274 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2109 | CVE-2026-54276 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N | yes |
| PYSEC-2026-2110 | CVE-2026-54277 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2111 | CVE-2026-54278 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2112 | CVE-2026-54279 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2113 | CVE-2026-54280 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-237 | CVE-2026-54275 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-3545 | CVE-2026-69244 | none | yes | |
| PYSEC-2026-3546 | CVE-2026-69243 | none | yes | |
| PYSEC-2026-3547 | CVE-2026-59881 | none | yes | |
| GHSA-5p39-cfhj-2xmp | CVE-2026-64847 | medium | yes | |
| GHSA-82r6-8w77-94w6 | CVE-2026-63374 | critical | yes | |
| PYSEC-2026-4024 | CVE-2026-64847 | none | yes | |
| PYSEC-2026-4025 | CVE-2026-63374 | none | yes | |
| GHSA-6v38-4h7w-rj9h | CVE-2026-96760 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-7vr2-2fgp-9w7p | CVE-2026-114615 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-8m4g-j4wp-wgcg | CVE-2026-114616 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-c5mf-xmp2-59rc | CVE-2026-114617 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:L/A:N | yes |
| GHSA-c73q-w75p-j82v | CVE-2026-116672 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-fch4-3c6x-j4gc | CVE-2026-114618 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-jj7h-c3hg-m23x | CVE-2026-114614 | low | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N | yes |
| GHSA-jj8c-mmj3-mmgv | CVE-2026-41425 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:N | yes |
| GHSA-q686-2qmg-hqc7 | CVE-2026-114619 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:L/I:L/A:N | yes |
| GHSA-r95x-qfjj-fjj2 | CVE-2026-44681 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N | yes |
Showing 50 of 299 vulnerabilities.
Background: What a vulnerability scan can and cannot prove →
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 →
follow_up_research Follow Up Research ~77
Grounded follow-up over a prior guided research result. Use searchSessionId from research and ask one specific question. This tool answers only when the saved evidence is strong enough; otherwise it returns an explicit abstention or insufficient-evidence response plus next actions.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | yes | – |
| searchSessionId | string | yes | – |
No output schema declared.
No examples provided.
get_runtime_status Get Runtime Status ~44
Guided runtime and provider-status summary. Use this to confirm the active tool profile, transport, effective smart provider, enabled coverage, and high-level warnings without reading low-level diagnostics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
inspect_source Inspect Source ~67
Inspect one source from a prior guided research result. Pass the searchSessionId and a source id from the research response to get provenance, trust state, source-access details, and the best direct-read follow-through.
| Name | Type | Req | Description |
|---|---|---|---|
| searchSessionId | string | yes | – |
| sourceId | string | yes | – |
No output schema declared.
No examples provided.
research Research ~193
Default guided entry point for low-context research requests. Use this for topic discovery, known-item recovery, citation repair, and regulatory or species-history questions when you want one trust-graded response instead of choosing among raw tools. The server picks the safest retrieval path, returns a compact evidence summary plus source records, and abstains or marks partial results when evidence is weak, off-topic, or incomplete.
| Name | Type | Req | Description |
|---|---|---|---|
| focus | string | – | Optional focus hint to steer the research goal. |
| latencyProfile | string | – | Research depth profile: fast, balanced, or deep. Default is balanced. |
| limit | integer | – | Max evidence-bearing sources to keep in the guided result set (default 5, max 10). |
| query | string | yes | – |
| venue | string | – | Optional venue hint to narrow the request. |
| year | string | – | Optional year or year range hint, e.g. 2022:2025. |
No output schema declared.
No examples provided.
resolve_reference Resolve Reference ~77
Resolve one reference-like input into the safest next anchor. Accepts citations, DOI strings, DOI URLs, arXiv IDs, title fragments, and regulatory references. Returns the best match when one is trustworthy, alternatives when ambiguity remains, and direct next actions when the input should pivot into a primary-source path.
| Name | Type | Req | Description |
|---|---|---|---|
| reference | string | yes | – |
No output schema declared.
No examples provided.
How do I install the Paper Chaser MCP server?
Paper Chaser MCP runs locally as a container image, launched with docker run --rm -i ghcr.io/joshuasundance-swca/paper-chaser-mcp:0.2.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/joshuasundance-swca/paper-chaser-mcp:0.2.2
claude mcp add joshuasundance-swca-paper-chaser-mcp -- docker run --rm -i ghcr.io/joshuasundance-swca/paper-chaser-mcp:0.2.2
What is the Paper Chaser MCP server?
Paper Chaser MCP is listed in the public MCP registry as io.github.joshuasundance-swca/paper-chaser-mcp. MCP server for academic papers, citations, authors, ECOS dossiers, and Federal Register text. This page covers its container image (ghcr.io/joshuasundance-swca/paper-chaser-mcp:0.2.2).
Is the Paper Chaser MCP server safe to use?
Paper Chaser MCP scores 55 out of 100 on VerifyMCP. The SBOM its publisher attached lists packages with 299 known advisories as of 4 November 2026. We do not grade that SBOM, as nothing verifies it. 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 Paper Chaser MCP server expose?
Paper Chaser MCP exposes 5 tools: research, follow_up_research, resolve_reference, inspect_source, get_runtime_status. Their descriptions and schemas cost roughly 458 tokens of context every time the server is loaded.
Is the Paper Chaser MCP server still maintained?
Paper Chaser MCP 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 Paper Chaser MCP server under?
Paper Chaser MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.