Adaptive Graph Of ThoughtsBLOCK
LLM Reasoning Framework for Scientific Research
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/saptadey-adaptive-graph-of-thoughts-mcp-server)
[](https://saptadey.github.io/Adaptive-Graph-of-Thoughts-MCP-server/) [](https://www.python.org/downloads/) [](LICENSE) [](Dockerfile) [](https://fastapi.tiangolo.com) [](https://networkx.org) [](CHANGELOG.md) [](https://smithery.ai/server/@SaptaDey/graph-of-thought-mcp) [](https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server/actions/workflows/codacy.yml) [](https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server/actions/workflows/codeql.yml) [](https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server/actions/workflows/dependabot/dependabot-updates) [](https://mseep.ai/app/b56538c9-7a30-45b3-851c-447fe2eb24a6)
🚀 Next-Generation AI Reasoning Framework for Scientific Research
*Leveraging graph structures to transfor
9e437c715750OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add adaptive-graph-of-thoughts-dxt-server --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env BASIC_AUTH_PASS=${BASIC_AUTH_PASS} --env BASIC_AUTH_USER=${BASIC_AUTH_USER} --env NEO4J_PASSWORD=${NEO4J_PASSWORD} -- npx -y [email protected]{
"mcpServers": {
"adaptive-graph-of-thoughts-dxt-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"BASIC_AUTH_PASS": "${BASIC_AUTH_PASS}",
"BASIC_AUTH_USER": "${BASIC_AUTH_USER}",
"NEO4J_PASSWORD": "${NEO4J_PASSWORD}"
}
}
}
}Exposed tools (13)
13 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_research_hypothesis | read | Hypothesis evaluation with confidence scoring and evidence integration |
analyze_research_question | read | Generate comprehensive analysis of a scientific research question |
constraints | read | Any constraints or limitations to consider |
domain | read | Scientific domain or field |
explore_scientific_relationships | read | Concept relationship mapping through graph-based analysis |
hypothesis_generator | read | Generate and evaluate multiple hypotheses for a given scientific problem |
literature_synthesis | read | Synthesize findings from multiple research papers into coherent insights |
problem_statement | read | The scientific problem to generate hypotheses for |
research_papers | read | List of research papers or citations to synthesize |
research_question | read | The research question to analyze |
scientific_reasoning_query | read | Advanced scientific reasoning with graph analysis using the ASR-GoT framework |
synthesis_focus | read | Specific aspect or theme to focus the synthesis on |
validate_scientific_claims | read | Evidence-based claim validation with external database integration |
Trust audit
BLOCKgrade F · trust 56/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (10 observation(s))
- Shell
- declared (6 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,s){"function"==typeof define&&define.amd?define(s):"object"==typeof exports?module.exports=s():s()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(i,e){"function"==typeof define&&define.amd?define(e):"object"==typeof exports?module.exports=e():e()(i.lunr)}(this,function(){return function(i){if(void 0===i)throw new Error("Lunr is not prsitemap.xml.gz
module = importlib.import_module(module_name)
f"Find statistical insignificance in {random.choice(['key_metric_A', 'key_metric_B'])}",!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not pr"APP_DATABASE_URL": "postgresql://test:test@localhost/testdb",
.codacy.yaml
.dxtignore
.eslintignore
.nojekyll
.pre-commit-config.yaml
tools_file = os.path.join(os.path.dirname(__file__), "../../../config/mcp_tools_definition.json")
tools_file = os.path.join(os.path.dirname(__file__), "../../../config/mcp_tools_definition.json")
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../../../git/src"))
"http://192.168.1.1:3000",
("http://192.168.1.1:3000/docs", True),typescript, @types/node
@modelcontextprotocol/inspector
@modelcontextprotocol/sdk, axios, zod
Adaptive-Graph-of-Thoughts-MCP-server.dxt
Gates applied: no_behavioural_pass.
9e437c715750full audit observations/trust-audit/mcp-server/saptadey__adaptive-graph-of-thoughts.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9e437c715750 | BLOCK | F | 56 | first audit |
Questions
What is the Adaptive Graph Of Thoughts MCP server?
LLM Reasoning Framework for Scientific Research
What tools does Adaptive Graph Of Thoughts expose?
13 in total: 13 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Adaptive Graph Of Thoughts safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (56/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Adaptive Graph Of Thoughts need?
It reads ANTHROPIC_API_KEY, BASIC_AUTH_PASS, BASIC_AUTH_USER, NEO4J_PASSWORD, OPENAI_API_KEY, PUBMED_API_KEY, SECRETS_PROVIDER and VAULT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Adaptive Graph Of Thoughts run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as adaptive-graph-of-thoughts-dxt-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (9e437c715750), read on 2026-10-08. The repository is watched and re-audited when it changes.